[03/31 10:13:17] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 10:13:18] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 10:13:18] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False) [03/31 10:13:18] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 10:13:18] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 10:13:18] c2.utils.env.env INFO: Using a generated random seed 18309802 [03/31 10:13:18] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 14:26:06] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 14:26:06] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 14:26:06] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False) [03/31 14:26:06] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 14:26:06] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 14:26:06] c2.utils.env.env INFO: Using a generated random seed 6765081 [03/31 14:26:06] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 14:26:23] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.48 seconds. [03/31 14:26:23] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 14:26:27] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 14:26:30] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 14:26:30] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 14:26:32] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 14:26:32] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 14:26:36] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 14:26:36] c2.utils.file.file_io INFO: Downloading https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl ... [03/31 14:26:36] c2.utils.file.download INFO: Downloading from https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl ... [03/31 14:27:29] c2.utils.file.download INFO: Successfully downloaded /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl. 102465407 bytes. [03/31 14:27:29] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 14:27:29] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 14:27:29] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 6765081 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 14:27:29] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 6765081 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 14:27:29] c2.engine.runner INFO: Starting training from iteration 0 [03/31 14:27:29] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 172, in run_step data = next(self._data_loader_iter) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 363, in __next__ data = self._next_data() File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 989, in _next_data return self._process_data(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1014, in _process_data data.reraise() File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/_utils.py", line 395, in reraise raise self.exc_type(msg) FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 185, in _worker_loop data = fetcher.fetch(index) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/utils/data/dataset.py", line 207, in __getitem__ return self.datasets[dataset_idx][sample_idx] File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/data/datasets/coco.py", line 140, in __getitem__ image = read_image(dataset_dict["file_name"], format=self.data_format) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/data/detection_utils.py", line 154, in read_image with PathManager.open(file_name, "rb") as f: File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/utils/file/file_io.py", line 358, in open return PathManager.__get_path_handler(path)._open(path, mode) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/utils/file/file_io.py", line 218, in _open return open(path, mode) FileNotFoundError: [Errno 2] No such file or directory: '/home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/train2017/000000537349.jpg' [03/31 14:27:29] c2.engine.hooks INFO: Total training time: 0:00:00 (0:00:00 on hooks) [03/31 14:40:10] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 14:40:11] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 14:40:11] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False) [03/31 14:40:11] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 14:40:11] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 14:40:11] c2.utils.env.env INFO: Using a generated random seed 11519340 [03/31 14:40:11] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 14:40:27] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.58 seconds. [03/31 14:40:28] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 14:40:32] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 14:40:35] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 14:40:35] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 14:40:37] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 14:40:37] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 14:40:41] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 14:40:41] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 14:40:41] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 14:40:41] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 11519340 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 14:40:41] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 11519340 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 14:40:41] c2.engine.runner INFO: Starting training from iteration 0 [03/31 14:40:42] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 185, in run_step loss_dict = self.model(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "../yolof_base/yolof.py", line 132, in forward losses = self.losses( File "../yolof_base/yolof.py", line 210, in losses dist.all_reduce(num_foreground) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 935, in all_reduce _check_default_pg() File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 209, in _check_default_pg assert _default_pg is not None, \ AssertionError: Default process group is not initialized [03/31 14:40:42] c2.engine.hooks INFO: Total training time: 0:00:01 (0:00:00 on hooks) [03/31 14:49:14] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 14:49:14] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 14:49:14] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False) [03/31 14:49:14] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 14:49:14] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 14:49:14] c2.utils.env.env INFO: Using a generated random seed 14887287 [03/31 14:49:14] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 14:49:31] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.33 seconds. [03/31 14:49:31] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 14:49:35] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 14:49:38] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 14:49:38] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 14:49:40] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 14:49:40] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 14:49:43] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 14:49:43] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 14:49:43] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 14:49:43] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 14887287 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 14:49:43] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 14887287 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 14:49:43] c2.engine.runner INFO: Starting training from iteration 0 [03/31 14:49:46] c2.utils.dump.events INFO: eta: N/A iter: 1/180000 total_loss: 2.176 loss_cls: 1.323 loss_box_reg: 0.853 data_time: 0.2184 lr: 0.000010 max_mem: 4576M [03/31 14:49:46] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 185, in run_step loss_dict = self.model(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "../yolof_base/yolof.py", line 121, in forward features = self.backbone(images.tensor) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/backbone/resnet.py", line 628, in forward x = self.stem(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/backbone/resnet.py", line 550, in forward x = self.conv1(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/layers/wrappers.py", line 97, in forward x = self.norm(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/layers/batch_norm.py", line 51, in forward return x * scale + bias RuntimeError: CUDA out of memory. Tried to allocate 522.00 MiB (GPU 0; 5.79 GiB total capacity; 1.70 GiB already allocated; 535.25 MiB free; 4.14 GiB reserved in total by PyTorch) [03/31 14:49:46] c2.engine.hooks INFO: Total training time: 0:00:00 (0:00:00 on hooks) [03/31 15:15:02] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 15:15:02] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 15:15:02] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False) [03/31 15:15:02] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 15:15:02] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 15:15:02] c2.utils.env.env INFO: Using a generated random seed 2716582 [03/31 15:15:02] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 15:15:19] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.49 seconds. [03/31 15:15:19] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 15:15:23] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 15:15:26] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 15:15:26] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 15:15:28] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 15:15:28] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 15:15:31] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 15:15:31] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 15:15:32] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 15:15:32] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 2716582 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 15:15:32] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 2716582 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 15:15:32] c2.engine.runner INFO: Starting training from iteration 0 [03/31 15:15:33] c2.utils.dump.events INFO: eta: N/A iter: 1/180000 total_loss: 2.141 loss_cls: 1.288 loss_box_reg: 0.853 data_time: 0.0604 lr: 0.000010 max_mem: 4576M [03/31 15:15:34] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 185, in run_step loss_dict = self.model(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "../yolof_base/yolof.py", line 121, in forward features = self.backbone(images.tensor) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/backbone/resnet.py", line 628, in forward x = self.stem(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/backbone/resnet.py", line 550, in forward x = self.conv1(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/layers/wrappers.py", line 97, in forward x = self.norm(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/layers/batch_norm.py", line 51, in forward return x * scale + bias RuntimeError: CUDA out of memory. Tried to allocate 522.00 MiB (GPU 0; 5.79 GiB total capacity; 1.70 GiB already allocated; 514.12 MiB free; 4.14 GiB reserved in total by PyTorch) [03/31 15:15:34] c2.engine.hooks INFO: Total training time: 0:00:00 (0:00:00 on hooks) [03/31 15:20:33] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 15:20:33] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 15:20:33] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=0, num_machines=1, opts=[], resume=False) [03/31 15:20:33] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 15:20:33] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 15:20:33] c2.utils.env.env INFO: Using a generated random seed 33707855 [03/31 15:20:33] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 15:20:50] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.47 seconds. [03/31 15:20:50] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 15:20:54] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 15:20:57] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 15:20:57] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 15:20:59] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 15:20:59] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 15:21:02] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 15:21:02] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 15:21:02] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 15:21:03] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 15:21:03] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 33707855 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 15:21:03] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 8, │ │ │ 'IMS_PER_DEVICE': 8, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 33707855 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 15:21:03] c2.engine.runner INFO: Starting training from iteration 0 [03/31 15:21:05] c2.utils.dump.events INFO: eta: N/A iter: 1/180000 total_loss: 2.202 loss_cls: 1.320 loss_box_reg: 0.883 data_time: 0.1088 lr: 0.000010 max_mem: 4576M [03/31 15:21:05] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 185, in run_step loss_dict = self.model(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "../yolof_base/yolof.py", line 121, in forward features = self.backbone(images.tensor) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/backbone/resnet.py", line 628, in forward x = self.stem(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/backbone/resnet.py", line 550, in forward x = self.conv1(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/layers/wrappers.py", line 97, in forward x = self.norm(x) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/layers/batch_norm.py", line 51, in forward return x * scale + bias RuntimeError: CUDA out of memory. Tried to allocate 522.00 MiB (GPU 0; 5.79 GiB total capacity; 1.70 GiB already allocated; 513.88 MiB free; 4.14 GiB reserved in total by PyTorch) [03/31 15:21:05] c2.engine.hooks INFO: Total training time: 0:00:00 (0:00:00 on hooks) [03/31 16:42:00] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 16:42:00] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 16:42:00] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=0, num_machines=1, opts=[], resume=False) [03/31 16:42:53] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 16:42:53] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 16:42:53] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=0, num_machines=1, opts=[], resume=False) [03/31 16:57:24] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 16:57:25] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 16:57:25] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=0, num_machines=1, opts=[], resume=False) [03/31 16:57:25] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 16:57:25] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 16:57:25] c2.utils.env.env INFO: Using a generated random seed 25272733 [03/31 16:57:25] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 16:57:41] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.51 seconds. [03/31 16:57:42] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 16:57:46] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 16:57:48] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 16:57:48] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 16:57:50] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 16:57:50] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 16:57:55] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 16:57:55] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 16:57:55] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 16:57:55] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 25272733 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 16:57:55] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 25272733 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 16:57:55] c2.engine.runner INFO: Starting training from iteration 0 [03/31 16:57:56] c2.utils.dump.events INFO: eta: N/A iter: 1/180000 total_loss: 2.245 loss_cls: 1.341 loss_box_reg: 0.904 data_time: 0.0070 lr: 0.000010 max_mem: 747M [03/31 16:57:59] c2.utils.dump.events INFO: eta: 7:50:19 iter: 20/180000 total_loss: 2.007 loss_cls: 1.312 loss_box_reg: 0.726 time: 0.1574 data_time: 0.0014 lr: 0.000200 max_mem: 1088M [03/31 16:58:02] c2.utils.dump.events INFO: eta: 7:40:38 iter: 40/180000 total_loss: 1.882 loss_cls: 1.189 loss_box_reg: 0.692 time: 0.1531 data_time: 0.0017 lr: 0.000400 max_mem: 1088M [03/31 16:58:06] c2.utils.dump.events INFO: eta: 7:40:40 iter: 60/180000 total_loss: 1.921 loss_cls: 1.136 loss_box_reg: 0.816 time: 0.1535 data_time: 0.0018 lr: 0.000600 max_mem: 1088M [03/31 16:58:09] c2.utils.dump.events INFO: eta: 7:40:55 iter: 80/180000 total_loss: 1.866 loss_cls: 1.045 loss_box_reg: 0.837 time: 0.1540 data_time: 0.0019 lr: 0.000799 max_mem: 1088M [03/31 16:58:12] c2.utils.dump.events INFO: eta: 7:40:47 iter: 100/180000 total_loss: 1.861 loss_cls: 1.121 loss_box_reg: 0.756 time: 0.1536 data_time: 0.0017 lr: 0.000999 max_mem: 1088M [03/31 16:58:16] c2.utils.dump.events INFO: eta: 7:40:44 iter: 120/180000 total_loss: 1.977 loss_cls: 1.151 loss_box_reg: 0.872 time: 0.1537 data_time: 0.0017 lr: 0.001199 max_mem: 1088M [03/31 16:58:19] c2.utils.dump.events INFO: eta: 7:43:24 iter: 140/180000 total_loss: 2.006 loss_cls: 1.138 loss_box_reg: 0.911 time: 0.1545 data_time: 0.0019 lr: 0.001399 max_mem: 1088M [03/31 16:58:22] c2.utils.dump.events INFO: eta: 7:45:48 iter: 160/180000 total_loss: 2.231 loss_cls: 1.148 loss_box_reg: 0.994 time: 0.1547 data_time: 0.0018 lr: 0.001599 max_mem: 1092M [03/31 16:58:26] c2.utils.dump.events INFO: eta: 7:46:15 iter: 180/180000 total_loss: 2.018 loss_cls: 1.122 loss_box_reg: 0.914 time: 0.1547 data_time: 0.0018 lr: 0.001799 max_mem: 1102M [03/31 16:58:29] c2.utils.dump.events INFO: eta: 7:45:00 iter: 200/180000 total_loss: 2.099 loss_cls: 1.096 loss_box_reg: 0.999 time: 0.1544 data_time: 0.0018 lr: 0.001999 max_mem: 1102M [03/31 16:58:32] c2.utils.dump.events INFO: eta: 7:42:25 iter: 220/180000 total_loss: 2.194 loss_cls: 1.126 loss_box_reg: 0.996 time: 0.1542 data_time: 0.0017 lr: 0.002199 max_mem: 1102M [03/31 16:58:36] c2.utils.dump.events INFO: eta: 7:42:22 iter: 240/180000 total_loss: 2.172 loss_cls: 1.145 loss_box_reg: 0.989 time: 0.1541 data_time: 0.0018 lr: 0.002398 max_mem: 1102M [03/31 16:58:39] c2.utils.dump.events INFO: eta: 7:41:41 iter: 260/180000 total_loss: 2.325 loss_cls: 1.275 loss_box_reg: 1.092 time: 0.1540 data_time: 0.0018 lr: 0.002598 max_mem: 1102M [03/31 16:58:42] c2.utils.dump.events INFO: eta: 7:42:16 iter: 280/180000 total_loss: 2.295 loss_cls: 1.229 loss_box_reg: 1.017 time: 0.1539 data_time: 0.0017 lr: 0.002798 max_mem: 1102M [03/31 16:58:45] c2.utils.dump.events INFO: eta: 7:41:35 iter: 300/180000 total_loss: 2.151 loss_cls: 1.236 loss_box_reg: 0.934 time: 0.1538 data_time: 0.0018 lr: 0.002998 max_mem: 1102M [03/31 16:58:49] c2.utils.dump.events INFO: eta: 7:40:18 iter: 320/180000 total_loss: 2.250 loss_cls: 1.207 loss_box_reg: 0.986 time: 0.1535 data_time: 0.0017 lr: 0.003198 max_mem: 1102M [03/31 16:58:52] c2.utils.dump.events INFO: eta: 7:40:08 iter: 340/180000 total_loss: 3.251 loss_cls: 2.344 loss_box_reg: 0.909 time: 0.1535 data_time: 0.0016 lr: 0.003398 max_mem: 1102M [03/31 16:58:55] c2.utils.dump.events INFO: eta: 7:40:05 iter: 360/180000 total_loss: 2.553 loss_cls: 1.765 loss_box_reg: 0.803 time: 0.1537 data_time: 0.0017 lr: 0.003598 max_mem: 1102M [03/31 16:58:59] c2.utils.dump.events INFO: eta: 7:39:59 iter: 380/180000 total_loss: 2.214 loss_cls: 1.365 loss_box_reg: 0.749 time: 0.1537 data_time: 0.0017 lr: 0.003797 max_mem: 1102M [03/31 16:59:02] c2.utils.dump.events INFO: eta: 7:39:52 iter: 400/180000 total_loss: 2.612 loss_cls: 1.695 loss_box_reg: 0.919 time: 0.1537 data_time: 0.0019 lr: 0.003997 max_mem: 1102M [03/31 16:59:06] c2.utils.dump.events INFO: eta: 7:39:14 iter: 420/180000 total_loss: 3.752 loss_cls: 2.968 loss_box_reg: 0.830 time: 0.1536 data_time: 0.0018 lr: 0.004197 max_mem: 1102M [03/31 16:59:09] c2.utils.dump.events INFO: eta: 7:38:48 iter: 440/180000 total_loss: 2.087 loss_cls: 1.180 loss_box_reg: 0.855 time: 0.1536 data_time: 0.0017 lr: 0.004397 max_mem: 1102M [03/31 16:59:12] c2.utils.dump.events INFO: eta: 7:38:40 iter: 460/180000 total_loss: 2.057 loss_cls: 1.087 loss_box_reg: 0.794 time: 0.1536 data_time: 0.0018 lr: 0.004597 max_mem: 1102M [03/31 16:59:15] c2.utils.dump.events INFO: eta: 7:37:54 iter: 480/180000 total_loss: 2.162 loss_cls: 1.183 loss_box_reg: 0.935 time: 0.1532 data_time: 0.0016 lr: 0.004797 max_mem: 1102M [03/31 16:59:19] c2.utils.dump.events INFO: eta: 7:37:46 iter: 500/180000 total_loss: 1.871 loss_cls: 1.065 loss_box_reg: 0.820 time: 0.1533 data_time: 0.0017 lr: 0.004997 max_mem: 1102M [03/31 16:59:22] c2.utils.dump.events INFO: eta: 7:37:58 iter: 520/180000 total_loss: 1.882 loss_cls: 1.054 loss_box_reg: 0.816 time: 0.1534 data_time: 0.0018 lr: 0.005197 max_mem: 1102M [03/31 16:59:26] c2.utils.dump.events INFO: eta: 7:38:28 iter: 540/180000 total_loss: 1.837 loss_cls: 1.100 loss_box_reg: 0.775 time: 0.1535 data_time: 0.0018 lr: 0.005396 max_mem: 1102M [03/31 16:59:29] c2.utils.dump.events INFO: eta: 7:38:41 iter: 560/180000 total_loss: 1.649 loss_cls: 1.004 loss_box_reg: 0.721 time: 0.1537 data_time: 0.0018 lr: 0.005596 max_mem: 1102M [03/31 16:59:32] c2.utils.dump.events INFO: eta: 7:38:59 iter: 580/180000 total_loss: 1.861 loss_cls: 1.169 loss_box_reg: 0.791 time: 0.1538 data_time: 0.0017 lr: 0.005796 max_mem: 1103M [03/31 16:59:36] c2.utils.dump.events INFO: eta: 7:38:51 iter: 600/180000 total_loss: 1.900 loss_cls: 1.150 loss_box_reg: 0.713 time: 0.1538 data_time: 0.0017 lr: 0.005996 max_mem: 1103M [03/31 16:59:39] c2.utils.dump.events INFO: eta: 7:38:56 iter: 620/180000 total_loss: 1.966 loss_cls: 1.067 loss_box_reg: 0.865 time: 0.1539 data_time: 0.0019 lr: 0.006196 max_mem: 1103M [03/31 16:59:42] c2.utils.dump.events INFO: eta: 7:39:10 iter: 640/180000 total_loss: 1.817 loss_cls: 1.126 loss_box_reg: 0.699 time: 0.1538 data_time: 0.0018 lr: 0.006396 max_mem: 1103M [03/31 16:59:46] c2.utils.dump.events INFO: eta: 7:39:07 iter: 660/180000 total_loss: 1.732 loss_cls: 1.007 loss_box_reg: 0.782 time: 0.1539 data_time: 0.0017 lr: 0.006596 max_mem: 1103M [03/31 16:59:49] c2.utils.dump.events INFO: eta: 7:39:13 iter: 680/180000 total_loss: 1.739 loss_cls: 1.088 loss_box_reg: 0.636 time: 0.1539 data_time: 0.0017 lr: 0.006795 max_mem: 1103M [03/31 16:59:52] c2.utils.dump.events INFO: eta: 7:39:08 iter: 700/180000 total_loss: 1.769 loss_cls: 1.064 loss_box_reg: 0.699 time: 0.1540 data_time: 0.0018 lr: 0.006995 max_mem: 1103M [03/31 16:59:56] c2.utils.dump.events INFO: eta: 7:39:09 iter: 720/180000 total_loss: 1.845 loss_cls: 1.004 loss_box_reg: 0.843 time: 0.1541 data_time: 0.0018 lr: 0.007195 max_mem: 1103M [03/31 16:59:59] c2.utils.dump.events INFO: eta: 7:39:05 iter: 740/180000 total_loss: 1.696 loss_cls: 1.044 loss_box_reg: 0.679 time: 0.1541 data_time: 0.0017 lr: 0.007395 max_mem: 1103M [03/31 17:00:02] c2.utils.dump.events INFO: eta: 7:39:01 iter: 760/180000 total_loss: 1.797 loss_cls: 0.906 loss_box_reg: 0.790 time: 0.1542 data_time: 0.0017 lr: 0.007595 max_mem: 1103M [03/31 17:00:06] c2.utils.dump.events INFO: eta: 7:38:53 iter: 780/180000 total_loss: 1.889 loss_cls: 1.084 loss_box_reg: 0.807 time: 0.1541 data_time: 0.0019 lr: 0.007795 max_mem: 1103M [03/31 17:00:09] c2.utils.dump.events INFO: eta: 7:38:57 iter: 800/180000 total_loss: 1.863 loss_cls: 1.110 loss_box_reg: 0.746 time: 0.1542 data_time: 0.0018 lr: 0.007995 max_mem: 1103M [03/31 17:00:13] c2.utils.dump.events INFO: eta: 7:38:54 iter: 820/180000 total_loss: 1.874 loss_cls: 1.024 loss_box_reg: 0.786 time: 0.1542 data_time: 0.0017 lr: 0.008195 max_mem: 1103M [03/31 17:00:16] c2.utils.dump.events INFO: eta: 7:39:01 iter: 840/180000 total_loss: 1.811 loss_cls: 1.038 loss_box_reg: 0.760 time: 0.1542 data_time: 0.0018 lr: 0.008394 max_mem: 1103M [03/31 17:00:19] c2.utils.dump.events INFO: eta: 7:39:31 iter: 860/180000 total_loss: 6.206 loss_cls: 5.393 loss_box_reg: 0.815 time: 0.1543 data_time: 0.0019 lr: 0.008594 max_mem: 1103M [03/31 17:00:23] c2.utils.dump.events INFO: eta: 7:39:38 iter: 880/180000 total_loss: 4.132 loss_cls: 3.189 loss_box_reg: 0.882 time: 0.1543 data_time: 0.0017 lr: 0.008794 max_mem: 1103M [03/31 17:00:26] c2.utils.dump.events INFO: eta: 7:39:50 iter: 900/180000 total_loss: 6.424 loss_cls: 5.496 loss_box_reg: 0.964 time: 0.1544 data_time: 0.0017 lr: 0.008994 max_mem: 1103M [03/31 17:00:29] c2.utils.dump.events INFO: eta: 7:39:47 iter: 920/180000 total_loss: 3.466 loss_cls: 2.203 loss_box_reg: 0.823 time: 0.1544 data_time: 0.0018 lr: 0.009194 max_mem: 1103M [03/31 17:00:33] c2.utils.dump.events INFO: eta: 7:40:15 iter: 940/180000 total_loss: 2.816 loss_cls: 2.042 loss_box_reg: 0.752 time: 0.1545 data_time: 0.0019 lr: 0.009394 max_mem: 1103M [03/31 17:00:34] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 185, in run_step loss_dict = self.model(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "../yolof_base/yolof.py", line 130, in forward indices = self.get_ground_truth( File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 15, in decorate_context return func(*args, **kwargs) File "../yolof_base/yolof.py", line 245, in get_ground_truth box_pred = self.box2box_transform.apply_deltas(box_delta, all_anchors) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/box_regression.py", line 92, in apply_deltas assert torch.isfinite( AssertionError: Box regression deltas become infinite or NaN! [03/31 17:00:34] c2.engine.hooks INFO: Overall training speed: 946 iterations in 0:02:26 (0.1546 s / it) [03/31 17:00:34] c2.engine.hooks INFO: Total training time: 0:02:38 (0:00:11 on hooks) [03/31 17:31:07] cvpods INFO: Rank of current process: 0. World size: 1 [03/31 17:31:07] cvpods INFO: Environment info: ---------------------- ---------------------------------------------------------------------------------- sys.platform linux Python 3.8.2 (default, Mar 26 2020, 15:53:00) [GCC 7.3.0] numpy 1.19.2 cvpods 0.1 @/home/xuxin/PycharmProjects/YOLOF-main/cvpods cvpods compiler GCC 9.3 cvpods CUDA compiler 10.1 cvpods arch flags sm_75 cvpods_ENV_MODULE PyTorch 1.6.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch PyTorch debug build False CUDA available True GPU 0 GeForce RTX 2060 CUDA_HOME /usr NVCC Cuda compilation tools, release 10.1, V10.1.243 Pillow 8.1.2 torchvision 0.7.0 @/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 4.5.1 ---------------------- ---------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 - CuDNN 7.6.3 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, [03/31 17:31:07] cvpods INFO: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False) [03/31 17:31:07] cvpods INFO: Running with full config: ╒═════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ -1 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├─────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ╘═════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 17:31:07] cvpods INFO: different config with base class: ╒═════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞═════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├─────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ╘═════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 17:31:07] c2.utils.env.env INFO: Using a generated random seed 8176287 [03/31 17:31:07] c2.data.build INFO: TransformGens used: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip(), RandomShift(max_shifts=32)] in training [03/31 17:31:24] c2.data.datasets.coco INFO: Loading /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json takes 16.46 seconds. [03/31 17:31:25] c2.data.datasets.coco INFO: Loaded 118287 images in COCO format from /home/xuxin/PycharmProjects/YOLOF-main/datasets/coco/annotations/instances_train2017.json [03/31 17:31:28] c2.data.base_dataset INFO: Removed 1021 images with no usable annotations. 117266 images left. [03/31 17:31:31] c2.data.base_dataset INFO: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances | |:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------| | person | 257253 | bicycle | 7056 | car | 43533 | | motorcycle | 8654 | airplane | 5129 | bus | 6061 | | train | 4570 | truck | 9970 | boat | 10576 | | traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 | | parking meter | 1283 | bench | 9820 | bird | 10542 | | cat | 4766 | dog | 5500 | horse | 6567 | | sheep | 9223 | cow | 8014 | elephant | 5484 | | bear | 1294 | zebra | 5269 | giraffe | 5128 | | backpack | 8714 | umbrella | 11265 | handbag | 12342 | | tie | 6448 | suitcase | 6112 | frisbee | 2681 | | skis | 6623 | snowboard | 2681 | sports ball | 6299 | | kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 | | skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 | | bottle | 24070 | wine glass | 7839 | cup | 20574 | | fork | 5474 | knife | 7760 | spoon | 6159 | | bowl | 14323 | banana | 9195 | apple | 5776 | | sandwich | 4356 | orange | 6302 | broccoli | 7261 | | carrot | 7758 | hot dog | 2884 | pizza | 5807 | | donut | 7005 | cake | 6296 | chair | 38073 | | couch | 5779 | potted plant | 8631 | bed | 4192 | | dining table | 15695 | toilet | 4149 | tv | 5803 | | laptop | 4960 | mouse | 2261 | remote | 5700 | | keyboard | 2854 | cell phone | 6422 | microwave | 1672 | | oven | 3334 | toaster | 225 | sink | 5609 | | refrigerator | 2634 | book | 24077 | clock | 6320 | | vase | 6577 | scissors | 1464 | teddy bear | 4729 | | hair drier | 198 | toothbrush | 1945 | | | | total | 849949 | | | | | [03/31 17:31:31] c2.data.build INFO: Using training sampler DistributedGroupSampler [03/31 17:31:33] c2.modeling.nn_utils.module_converter WARNING: SyncBN used with 1GPU, auto convert to BatchNorm [03/31 17:31:33] cvpods INFO: Model: YOLOF( (backbone): ResNet( (stem): BasicStem( (conv1): Conv2d( 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (activation): ReLU(inplace=True) (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (res2): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv2): Conv2d( 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05) ) (conv3): Conv2d( 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) ) ) (res3): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv2): Conv2d( 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05) ) (conv3): Conv2d( 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) ) ) (res4): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (3): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (4): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) (5): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv2): Conv2d( 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05) ) (conv3): Conv2d( 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05) ) ) ) (res5): Sequential( (0): BottleneckBlock( (shortcut): Conv2d( 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) (activation): ReLU(inplace=True) (conv1): Conv2d( 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (1): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) (2): BottleneckBlock( (activation): ReLU(inplace=True) (conv1): Conv2d( 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv2): Conv2d( 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05) ) (conv3): Conv2d( 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05) ) ) ) ) (encoder): DilatedEncoder( (lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1)) (lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (dilated_encoder_blocks): Sequential( (0): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (2): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (3): Bottleneck( (conv1): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (decoder): Decoder( (cls_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (bbox_subnet): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (11): ReLU(inplace=True) ) (cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (anchor_generator): DefaultAnchorGenerator( (cell_anchors): BufferList() ) (matcher): UniformMatcher() ) [03/31 17:31:38] c2.checkpoint.checkpoint INFO: Loading checkpoint from detectron2://ImageNetPretrained/MSRA/R-50.pkl [03/31 17:31:38] c2.utils.file.file_io INFO: URL https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl cached in /home/xuxin/.torch/cvpods_cache/detectron2/ImageNetPretrained/MSRA/R-50.pkl [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: Remapping C2 weights ...... [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: backbone.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7) [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: Some model parameters are not in the checkpoint: anchor_generator.cell_anchors.0 decoder.bbox_pred.{bias, weight} decoder.bbox_subnet.0.{bias, weight} decoder.bbox_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.10.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.3.{bias, weight} decoder.bbox_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.6.{bias, weight} decoder.bbox_subnet.7.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.bbox_subnet.9.{bias, weight} decoder.cls_score.{bias, weight} decoder.cls_subnet.0.{bias, weight} decoder.cls_subnet.1.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.cls_subnet.3.{bias, weight} decoder.cls_subnet.4.{bias, num_batches_tracked, running_mean, running_var, weight} decoder.object_pred.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.0.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.0.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.1.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.1.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.2.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.2.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv1.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv1.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv2.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv2.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.dilated_encoder_blocks.3.conv3.0.{bias, weight} encoder.dilated_encoder_blocks.3.conv3.1.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.fpn_conv.{bias, weight} encoder.fpn_norm.{bias, num_batches_tracked, running_mean, running_var, weight} encoder.lateral_conv.{bias, weight} encoder.lateral_norm.{bias, num_batches_tracked, running_mean, running_var, weight} pixel_mean pixel_std [03/31 17:31:38] c2.checkpoint.c2_model_loading INFO: The checkpoint contains parameters not used by the model: fc1000_b fc1000_w conv1_b [03/31 17:31:38] cvpods INFO: Running with full config: ╒════════════════════════╤═══════════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═══════════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │ │ │ 'ASPECT_RATIOS': [[1.0]], │ │ │ 'OFFSET': 0.0, │ │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │ │ │ 'AS_PRETRAIN': False, │ │ │ 'BACKBONE': {'FREEZE_AT': 2}, │ │ │ 'DEVICE': 'cuda', │ │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │ │ │ 'FUSE_TYPE': 'sum', │ │ │ 'IN_FEATURES': [], │ │ │ 'NORM': '', │ │ │ 'OUT_CHANNELS': 256}, │ │ │ 'KEYPOINT_ON': False, │ │ │ 'LOAD_PROPOSALS': False, │ │ │ 'MASK_ON': False, │ │ │ 'NMS_TYPE': 'normal', │ │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │ │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │ │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │ │ │ 'DEEP_STEM': False, │ │ │ 'DEPTH': 50, │ │ │ 'NORM': 'FrozenBN', │ │ │ 'NUM_CLASSES': None, │ │ │ 'NUM_GROUPS': 1, │ │ │ 'OUT_FEATURES': ['res5'], │ │ │ 'RES2_OUT_CHANNELS': 256, │ │ │ 'RES5_DILATION': 1, │ │ │ 'STEM_OUT_CHANNELS': 64, │ │ │ 'STRIDE_IN_1X1': True, │ │ │ 'WIDTH_PER_GROUP': 64, │ │ │ 'ZERO_INIT_RESIDUAL': False}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': 800})], │ │ │ 'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}, │ │ │ 'FORMAT': 'BGR', │ │ │ 'MASK_FORMAT': 'polygon'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │ │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │ │ │ 'PROPOSAL_FILES_TEST': [], │ │ │ 'PROPOSAL_FILES_TRAIN': [], │ │ │ 'TEST': ['coco_2017_val'], │ │ │ 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │ │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │ │ │ 'NUM_WORKERS': 8, │ │ │ 'REPEAT_THRESHOLD': 0.0, │ │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │ │ │ 'CHECKPOINT_PERIOD': 40000, │ │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │ │ │ 'CLIP_VALUE': 1.0, │ │ │ 'ENABLED': False, │ │ │ 'NORM_TYPE': 2.0}, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'GAMMA': 0.1, │ │ │ 'MAX_EPOCH': None, │ │ │ 'MAX_ITER': 180000, │ │ │ 'NAME': 'WarmupMultiStepLR', │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500, │ │ │ 'WARMUP_METHOD': 'linear'}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, │ │ │ 'BASE_LR': 0.015, │ │ │ 'BIAS_LR_FACTOR': 1.0, │ │ │ 'MOMENTUM': 0.9, │ │ │ 'NAME': 'D2SGD', │ │ │ 'WEIGHT_DECAY': 0.0001, │ │ │ 'WEIGHT_DECAY_NORM': 0.0}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TEST │ {'AUG': {'ENABLED': False, │ │ │ 'EXTRA_SIZES': [], │ │ │ 'FLIP': True, │ │ │ 'MAX_SIZE': 4000, │ │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │ │ │ 'SCALE_FILTER': False, │ │ │ 'SCALE_RANGES': []}, │ │ │ 'DETECTIONS_PER_IMAGE': 100, │ │ │ 'EVAL_PERIOD': 0, │ │ │ 'EXPECTED_RESULTS': [], │ │ │ 'KEYPOINT_OKS_SIGMAS': [], │ │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ TRAINER │ {'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │ │ │ 'NAME': 'DefaultRunner', │ │ │ 'WINDOW_SIZE': 20} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ OUTPUT_DIR │ './output' │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ SEED │ 8176287 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ CUDNN_BENCHMARK │ False │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ VIS_PERIOD │ 0 │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ GLOBAL │ {'DUMP_TEST': False, 'DUMP_TRAIN': True, 'HACK': 1.0} │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼───────────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═══════════════════════════════════════════════════════════════════════════╛ [03/31 17:31:38] cvpods INFO: different config with base class: ╒════════════════════════╤═════════════════════════════════════════════════════════════════════╕ │ config params │ values │ ╞════════════════════════╪═════════════════════════════════════════════════════════════════════╡ │ MODEL │ {'ANCHOR_GENERATOR': {'ASPECT_RATIOS': [[1.0]]}, │ │ │ 'RESNETS': {'DEPTH': 50, 'OUT_FEATURES': ['res5']}, │ │ │ 'WEIGHTS': 'detectron2://ImageNetPretrained/MSRA/R-50.pkl', │ │ │ 'YOLOF': {'ADD_CTR_CLAMP': True, │ │ │ 'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │ │ │ 'CTR_CLAMP': 32, │ │ │ 'DECODER': {'ACTIVATION': 'ReLU', │ │ │ 'CLS_NUM_CONVS': 2, │ │ │ 'IN_CHANNELS': 512, │ │ │ 'NORM': 'BN', │ │ │ 'NUM_ANCHORS': 5, │ │ │ 'NUM_CLASSES': 80, │ │ │ 'PRIOR_PROB': 0.01, │ │ │ 'REG_NUM_CONVS': 4}, │ │ │ 'ENCODER': {'ACTIVATION': 'ReLU', │ │ │ 'BLOCK_DILATIONS': [2, 4, 6, 8], │ │ │ 'BLOCK_MID_CHANNELS': 128, │ │ │ 'IN_FEATURES': ['res5'], │ │ │ 'NORM': 'BN', │ │ │ 'NUM_CHANNELS': 512, │ │ │ 'NUM_RESIDUAL_BLOCKS': 4}, │ │ │ 'FOCAL_LOSS_ALPHA': 0.25, │ │ │ 'FOCAL_LOSS_GAMMA': 2.0, │ │ │ 'MATCHER_TOPK': 4, │ │ │ 'NEG_IGNORE_THRESHOLD': 0.7, │ │ │ 'NMS_THRESH_TEST': 0.6, │ │ │ 'POS_IGNORE_THRESHOLD': 0.15, │ │ │ 'SCORE_THRESH_TEST': 0.05, │ │ │ 'TOPK_CANDIDATES_TEST': 1000}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ INPUT │ {'AUG': {'TRAIN_PIPELINES': [('ResizeShortestEdge', │ │ │ {'max_size': 1333, │ │ │ 'sample_style': 'choice', │ │ │ 'short_edge_length': (800,)}), │ │ │ ('RandomFlip', {}), │ │ │ ('RandomShift', {'max_shifts': 32})]}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATASETS │ {'TEST': ['coco_2017_val'], 'TRAIN': ['coco_2017_train']} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ DATALOADER │ {'NUM_WORKERS': 8} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SOLVER │ {'CHECKPOINT_PERIOD': 40000, │ │ │ 'IMS_PER_BATCH': 1, │ │ │ 'IMS_PER_DEVICE': 1, │ │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │ │ │ 'MAX_ITER': 180000, │ │ │ 'STEPS': [120000, 160000], │ │ │ 'WARMUP_FACTOR': 0.00066667, │ │ │ 'WARMUP_ITERS': 1500}, │ │ │ 'OPTIMIZER': {'BACKBONE_LR_FACTOR': 0.334, 'BASE_LR': 0.015}} │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ SEED │ 8176287 │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_backbone │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_anchor_generator │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_encoder │ │ ├────────────────────────┼─────────────────────────────────────────────────────────────────────┤ │ build_decoder │ │ ╘════════════════════════╧═════════════════════════════════════════════════════════════════════╛ [03/31 17:31:38] c2.engine.runner INFO: Starting training from iteration 0 [03/31 17:31:38] c2.utils.dump.events INFO: eta: N/A iter: 1/180000 total_loss: 2.240 loss_cls: 1.351 loss_box_reg: 0.889 data_time: 0.0152 lr: 0.000010 max_mem: 747M [03/31 17:31:42] c2.utils.dump.events INFO: eta: 7:47:12 iter: 20/180000 total_loss: 2.044 loss_cls: 1.278 loss_box_reg: 0.745 time: 0.1555 data_time: 0.0016 lr: 0.000200 max_mem: 1088M [03/31 17:31:45] c2.utils.dump.events INFO: eta: 7:30:13 iter: 40/180000 total_loss: 1.879 loss_cls: 1.172 loss_box_reg: 0.704 time: 0.1494 data_time: 0.0018 lr: 0.000400 max_mem: 1088M [03/31 17:31:48] c2.utils.dump.events INFO: eta: 7:30:55 iter: 60/180000 total_loss: 1.869 loss_cls: 1.102 loss_box_reg: 0.799 time: 0.1498 data_time: 0.0019 lr: 0.000600 max_mem: 1088M [03/31 17:31:51] c2.utils.dump.events INFO: eta: 7:35:52 iter: 80/180000 total_loss: 1.773 loss_cls: 1.016 loss_box_reg: 0.763 time: 0.1517 data_time: 0.0018 lr: 0.000799 max_mem: 1088M [03/31 17:31:55] c2.utils.dump.events INFO: eta: 7:37:07 iter: 100/180000 total_loss: 1.971 loss_cls: 1.135 loss_box_reg: 0.840 time: 0.1518 data_time: 0.0018 lr: 0.000999 max_mem: 1088M [03/31 17:31:58] c2.utils.dump.events INFO: eta: 7:38:42 iter: 120/180000 total_loss: 1.854 loss_cls: 1.076 loss_box_reg: 0.794 time: 0.1521 data_time: 0.0020 lr: 0.001199 max_mem: 1088M [03/31 17:32:01] c2.utils.dump.events INFO: eta: 7:38:53 iter: 140/180000 total_loss: 2.073 loss_cls: 1.121 loss_box_reg: 0.997 time: 0.1519 data_time: 0.0019 lr: 0.001399 max_mem: 1088M [03/31 17:32:05] c2.utils.dump.events INFO: eta: 7:41:02 iter: 160/180000 total_loss: 1.986 loss_cls: 1.075 loss_box_reg: 0.974 time: 0.1520 data_time: 0.0019 lr: 0.001599 max_mem: 1092M [03/31 17:32:08] c2.utils.dump.events INFO: eta: 7:41:10 iter: 180/180000 total_loss: 2.020 loss_cls: 1.077 loss_box_reg: 0.956 time: 0.1524 data_time: 0.0019 lr: 0.001799 max_mem: 1102M [03/31 17:32:11] c2.utils.dump.events INFO: eta: 7:40:56 iter: 200/180000 total_loss: 2.084 loss_cls: 1.095 loss_box_reg: 0.957 time: 0.1524 data_time: 0.0018 lr: 0.001999 max_mem: 1102M [03/31 17:32:15] c2.utils.dump.events INFO: eta: 7:41:04 iter: 220/180000 total_loss: 2.057 loss_cls: 1.113 loss_box_reg: 0.978 time: 0.1524 data_time: 0.0018 lr: 0.002199 max_mem: 1102M [03/31 17:32:18] c2.utils.dump.events INFO: eta: 7:41:03 iter: 240/180000 total_loss: 1.994 loss_cls: 1.121 loss_box_reg: 0.835 time: 0.1526 data_time: 0.0016 lr: 0.002398 max_mem: 1102M [03/31 17:32:21] c2.utils.dump.events INFO: eta: 7:41:28 iter: 260/180000 total_loss: 1.958 loss_cls: 1.049 loss_box_reg: 0.845 time: 0.1532 data_time: 0.0018 lr: 0.002598 max_mem: 1102M [03/31 17:32:25] c2.utils.dump.events INFO: eta: 7:41:46 iter: 280/180000 total_loss: 1.947 loss_cls: 1.130 loss_box_reg: 0.837 time: 0.1531 data_time: 0.0018 lr: 0.002798 max_mem: 1102M [03/31 17:32:28] c2.utils.dump.events INFO: eta: 7:41:00 iter: 300/180000 total_loss: 1.712 loss_cls: 1.014 loss_box_reg: 0.702 time: 0.1531 data_time: 0.0019 lr: 0.002998 max_mem: 1102M [03/31 17:32:31] c2.utils.dump.events INFO: eta: 7:43:02 iter: 320/180000 total_loss: 1.947 loss_cls: 1.136 loss_box_reg: 0.799 time: 0.1538 data_time: 0.0018 lr: 0.003198 max_mem: 1102M [03/31 17:32:35] c2.utils.dump.events INFO: eta: 7:43:28 iter: 340/180000 total_loss: 1.942 loss_cls: 1.132 loss_box_reg: 0.796 time: 0.1540 data_time: 0.0017 lr: 0.003398 max_mem: 1102M [03/31 17:32:38] c2.utils.dump.events INFO: eta: 7:42:35 iter: 360/180000 total_loss: 1.894 loss_cls: 1.127 loss_box_reg: 0.735 time: 0.1539 data_time: 0.0019 lr: 0.003598 max_mem: 1102M [03/31 17:32:41] c2.utils.dump.events INFO: eta: 7:42:32 iter: 380/180000 total_loss: 1.829 loss_cls: 1.072 loss_box_reg: 0.681 time: 0.1539 data_time: 0.0018 lr: 0.003797 max_mem: 1102M [03/31 17:32:45] c2.utils.dump.events INFO: eta: 7:42:13 iter: 400/180000 total_loss: 1.795 loss_cls: 1.090 loss_box_reg: 0.692 time: 0.1539 data_time: 0.0018 lr: 0.003997 max_mem: 1102M [03/31 17:32:48] c2.utils.dump.events INFO: eta: 7:42:26 iter: 420/180000 total_loss: 1.800 loss_cls: 1.062 loss_box_reg: 0.780 time: 0.1542 data_time: 0.0016 lr: 0.004197 max_mem: 1102M [03/31 17:32:52] c2.utils.dump.events INFO: eta: 7:43:07 iter: 440/180000 total_loss: 1.746 loss_cls: 0.984 loss_box_reg: 0.724 time: 0.1547 data_time: 0.0017 lr: 0.004397 max_mem: 1102M [03/31 17:32:55] c2.utils.dump.events INFO: eta: 7:42:52 iter: 460/180000 total_loss: 1.767 loss_cls: 1.037 loss_box_reg: 0.694 time: 0.1546 data_time: 0.0018 lr: 0.004597 max_mem: 1102M [03/31 17:32:58] c2.utils.dump.events INFO: eta: 7:42:20 iter: 480/180000 total_loss: 1.759 loss_cls: 1.022 loss_box_reg: 0.708 time: 0.1545 data_time: 0.0016 lr: 0.004797 max_mem: 1102M [03/31 17:33:02] c2.utils.dump.events INFO: eta: 7:43:01 iter: 500/180000 total_loss: 1.754 loss_cls: 1.032 loss_box_reg: 0.745 time: 0.1553 data_time: 0.0018 lr: 0.004997 max_mem: 1102M [03/31 17:33:06] c2.utils.dump.events INFO: eta: 7:43:54 iter: 520/180000 total_loss: 1.888 loss_cls: 1.086 loss_box_reg: 0.796 time: 0.1559 data_time: 0.0018 lr: 0.005197 max_mem: 1102M [03/31 17:33:09] c2.utils.dump.events INFO: eta: 7:44:50 iter: 540/180000 total_loss: 1.782 loss_cls: 1.053 loss_box_reg: 0.801 time: 0.1561 data_time: 0.0018 lr: 0.005396 max_mem: 1102M [03/31 17:33:13] c2.utils.dump.events INFO: eta: 7:44:59 iter: 560/180000 total_loss: 1.616 loss_cls: 0.991 loss_box_reg: 0.674 time: 0.1560 data_time: 0.0017 lr: 0.005596 max_mem: 1102M [03/31 17:33:16] c2.utils.dump.events INFO: eta: 7:45:01 iter: 580/180000 total_loss: 1.749 loss_cls: 1.057 loss_box_reg: 0.754 time: 0.1562 data_time: 0.0018 lr: 0.005796 max_mem: 1103M [03/31 17:33:19] c2.utils.dump.events INFO: eta: 7:45:03 iter: 600/180000 total_loss: 1.704 loss_cls: 1.019 loss_box_reg: 0.666 time: 0.1563 data_time: 0.0016 lr: 0.005996 max_mem: 1103M [03/31 17:33:23] c2.utils.dump.events INFO: eta: 7:45:04 iter: 620/180000 total_loss: 1.687 loss_cls: 0.958 loss_box_reg: 0.693 time: 0.1563 data_time: 0.0016 lr: 0.006196 max_mem: 1103M [03/31 17:33:26] c2.utils.dump.events INFO: eta: 7:45:02 iter: 640/180000 total_loss: 1.794 loss_cls: 1.082 loss_box_reg: 0.737 time: 0.1564 data_time: 0.0018 lr: 0.006396 max_mem: 1103M [03/31 17:33:30] c2.utils.dump.events INFO: eta: 7:45:20 iter: 660/180000 total_loss: 1.826 loss_cls: 1.069 loss_box_reg: 0.732 time: 0.1564 data_time: 0.0018 lr: 0.006596 max_mem: 1103M [03/31 17:33:33] c2.utils.dump.events INFO: eta: 7:45:23 iter: 680/180000 total_loss: 1.698 loss_cls: 1.037 loss_box_reg: 0.605 time: 0.1564 data_time: 0.0019 lr: 0.006795 max_mem: 1103M [03/31 17:33:36] c2.utils.dump.events INFO: eta: 7:45:29 iter: 700/180000 total_loss: 1.699 loss_cls: 0.992 loss_box_reg: 0.737 time: 0.1565 data_time: 0.0018 lr: 0.006995 max_mem: 1103M [03/31 17:33:40] c2.utils.dump.events INFO: eta: 7:45:36 iter: 720/180000 total_loss: 2.162 loss_cls: 1.183 loss_box_reg: 0.873 time: 0.1565 data_time: 0.0019 lr: 0.007195 max_mem: 1103M [03/31 17:33:43] c2.utils.dump.events INFO: eta: 7:45:33 iter: 740/180000 total_loss: 1.881 loss_cls: 1.162 loss_box_reg: 0.662 time: 0.1564 data_time: 0.0019 lr: 0.007395 max_mem: 1103M [03/31 17:33:46] c2.utils.dump.events INFO: eta: 7:45:19 iter: 760/180000 total_loss: 2.052 loss_cls: 1.210 loss_box_reg: 0.830 time: 0.1564 data_time: 0.0018 lr: 0.007595 max_mem: 1103M [03/31 17:33:50] c2.utils.dump.events INFO: eta: 7:45:08 iter: 780/180000 total_loss: 1.865 loss_cls: 1.106 loss_box_reg: 0.747 time: 0.1564 data_time: 0.0018 lr: 0.007795 max_mem: 1103M [03/31 17:33:53] c2.utils.dump.events INFO: eta: 7:45:33 iter: 800/180000 total_loss: 1.803 loss_cls: 1.099 loss_box_reg: 0.701 time: 0.1565 data_time: 0.0018 lr: 0.007995 max_mem: 1103M [03/31 17:33:57] c2.utils.dump.events INFO: eta: 7:45:24 iter: 820/180000 total_loss: 2.206 loss_cls: 1.264 loss_box_reg: 0.700 time: 0.1565 data_time: 0.0019 lr: 0.008195 max_mem: 1103M [03/31 17:34:00] c2.utils.dump.events INFO: eta: 7:45:10 iter: 840/180000 total_loss: 1.995 loss_cls: 1.171 loss_box_reg: 0.776 time: 0.1564 data_time: 0.0018 lr: 0.008394 max_mem: 1103M [03/31 17:34:03] c2.utils.dump.events INFO: eta: 7:45:07 iter: 860/180000 total_loss: 1.944 loss_cls: 1.101 loss_box_reg: 0.799 time: 0.1564 data_time: 0.0017 lr: 0.008594 max_mem: 1103M [03/31 17:34:07] c2.utils.dump.events INFO: eta: 7:44:45 iter: 880/180000 total_loss: 1.946 loss_cls: 1.142 loss_box_reg: 0.717 time: 0.1563 data_time: 0.0017 lr: 0.008794 max_mem: 1103M [03/31 17:34:10] c2.utils.dump.events INFO: eta: 7:44:36 iter: 900/180000 total_loss: 1.856 loss_cls: 1.034 loss_box_reg: 0.719 time: 0.1563 data_time: 0.0018 lr: 0.008994 max_mem: 1103M [03/31 17:34:13] c2.utils.dump.events INFO: eta: 7:44:20 iter: 920/180000 total_loss: 1.668 loss_cls: 1.109 loss_box_reg: 0.595 time: 0.1563 data_time: 0.0016 lr: 0.009194 max_mem: 1103M [03/31 17:34:17] c2.utils.dump.events INFO: eta: 7:44:17 iter: 940/180000 total_loss: 1.741 loss_cls: 1.060 loss_box_reg: 0.754 time: 0.1562 data_time: 0.0016 lr: 0.009394 max_mem: 1103M [03/31 17:34:20] c2.utils.dump.events INFO: eta: 7:44:13 iter: 960/180000 total_loss: 1.698 loss_cls: 0.931 loss_box_reg: 0.750 time: 0.1562 data_time: 0.0017 lr: 0.009594 max_mem: 1103M [03/31 17:34:24] c2.utils.dump.events INFO: eta: 7:44:08 iter: 980/180000 total_loss: 1.664 loss_cls: 1.024 loss_box_reg: 0.673 time: 0.1562 data_time: 0.0017 lr: 0.009793 max_mem: 1103M [03/31 17:34:24] c2.engine.base_runner ERROR: Exception during training: Traceback (most recent call last): File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 84, in train self.run_step() File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/engine/base_runner.py", line 185, in run_step loss_dict = self.model(data) File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "../yolof_base/yolof.py", line 130, in forward indices = self.get_ground_truth( File "/home/xuxin/anaconda3/envs/torch1.6/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 15, in decorate_context return func(*args, **kwargs) File "../yolof_base/yolof.py", line 245, in get_ground_truth box_pred = self.box2box_transform.apply_deltas(box_delta, all_anchors) File "/home/xuxin/PycharmProjects/YOLOF-main/cvpods/modeling/box_regression.py", line 92, in apply_deltas assert torch.isfinite( AssertionError: Box regression deltas become infinite or NaN! [03/31 17:34:24] c2.engine.hooks INFO: Overall training speed: 980 iterations in 0:02:33 (0.1563 s / it) [03/31 17:34:24] c2.engine.hooks INFO: Total training time: 0:02:45 (0:00:12 on hooks)