Some model parameters or buffers are not found in the checkpoint #4090
Description
Expected behavior:
It should load all my model weights.
SOS！Why detectron2 version==0.4，can not load my whole model weights?
Instructions To Reproduce the 🐛 Bug:
-
What exact command you run:
python projects/CenterNet2/train_net.py --config-file projects/CenterNet2/configs/OurNet_R101_DCN.yaml --eval-only MODEL.WEIGHTS D:\MyFile\dataset\model\processed+aerial_processes\OurNet_R101_DCN\model_0069999.pth -
Full logs or other relevant observations:
Command Line Args: Namespace(config_file='projects/CenterNet2/configs/OurNet_R101_DCN.yaml', dist_url='tcp://127.0.0.1:46263', eval_only=True, machine_rank=0, manual_device='', num_gpus=1
, num_machines=1, opts=['MODEL.WEIGHTS', 'D:\\MyFile\\dataset\\model\\processed+aerial_processes\\OurNet_R101_DCN\\model_0069499.pth'], resume=False)
Config 'projects/CenterNet2/configs/OurNet_R101_DCN.yaml' has no VERSION. Assuming it to be compatible with latest v2.
[03/19 20:45:12 detectron2]: Rank of current process: 0. World size: 1
[03/19 20:45:13 detectron2]: Environment info:
---------------------- --------------------------------------------------------------------------------------------------
sys.platform win32
Python 3.7.11 (default, Jul 27 2021, 09:42:29) [MSC v.1916 64 bit (AMD64)]
numpy 1.17.0
detectron2 0.6 @d:\myfile\projects\git projects\detectron2\detectron2
Compiler MSVC 192628806
CUDA compiler CUDA 10.2
detectron2 arch flags d:\myfile\projects\git projects\detectron2\detectron2\_C.cp37-win_amd64.pyd; cannot find cuobjdump
DETECTRON2_ENV_MODULE <not set>
PyTorch 1.10.2+cu102 @D:\MyFile\tool\Anaconda\lib\site-packages\torch
PyTorch debug build False
GPU available Yes
GPU 0 GeForce GTX 1660 Ti (arch=7.5)
Driver version 457.49
CUDA_HOME C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2
Pillow 8.3.1
torchvision 0.11.3+cu102 @D:\MyFile\tool\Anaconda\lib\site-packages\torchvision
torchvision arch flags D:\MyFile\tool\Anaconda\lib\site-packages\torchvision\_C.pyd; cannot find cuobjdump
fvcore 0.1.5
iopath 0.1.8
cv2 4.5.4-dev
---------------------- --------------------------------------------------------------------------------------------------
PyTorch built with:
- C++ Version: 199711
- MSVC 192829337
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
- OpenMP 2019
- LAPACK is enabled (usually provided by MKL)
- CPU capability usage: AVX2
- CUDA Runtime 10.2
- 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 7.6.5
- Magma 2.5.4
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.2, CUDNN_VERSION=7.6.5, CXX_COMPILER=C:/w/b/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /
w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -IC:/w/b/windows/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE
_PROFILER_USE_KINETO, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.2, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLO
G=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON,
[03/19 20:45:13 detectron2]: Command line arguments: Namespace(config_file='projects/CenterNet2/configs/OurNet_R101_DCN.yaml', dist_url='tcp://127.0.0.1:46263', eval_only=True, machine_ra
nk=0, manual_device='', num_gpus=1, num_machines=1, opts=['MODEL.WEIGHTS', 'D:\\MyFile\\dataset\\model\\processed+aerial_processes\\OurNet_R101_DCN\\model_0069499.pth'], resume=False)
[03/19 20:45:13 detectron2]: Contents of args.config_file=projects/CenterNet2/configs/OurNet_R101_DCN.yaml:
_BASE_: "Base-OurNet.yaml"
MODEL:
OURNET:
USE_DEFORMABLE: True
RESNETS:
DEPTH: 101
DEFORM_ON_PER_STAGE: [False, False, True, True] # on Res4, Res5
DEFORM_MODULATED: True
SOLVER:
IMS_PER_BATCH: 1
[03/19 20:45:13 detectron2]: Running with full config:
CUDNN_BENCHMARK: false
DATALOADER:
ASPECT_RATIO_GROUPING: true
FILTER_EMPTY_ANNOTATIONS: true
NUM_WORKERS: 4
REPEAT_THRESHOLD: 0.0
SAMPLER_TRAIN: TrainingSampler
DATASETS:
PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
PROPOSAL_FILES_TEST: []
PROPOSAL_FILES_TRAIN: []
TEST:
- test
TRAIN:
- train
- train_aerial
DEBUG: false
DEBUG_SHOW_NAME: false
GLOBAL:
HACK: 1.0
INPUT:
CROP:
ENABLED: false
SIZE:
- 0.9
- 0.9
TYPE: relative_range
CUSTOM_AUG: ''
FORMAT: BGR
MASK_FORMAT: polygon
MAX_SIZE_TEST: 3200
MAX_SIZE_TRAIN: 1200
MIN_SIZE_TEST: 1200
MIN_SIZE_TRAIN:
- 500
- 600
- 700
- 800
- 900
MIN_SIZE_TRAIN_SAMPLING: choice
RANDOM_FLIP: horizontal
SCALE_RANGE:
- 0.1
- 2.0
TEST_INPUT_TYPE: default
TEST_SIZE: 640
TRAIN_SIZE: 640
MODEL:
ANCHOR_GENERATOR:
ANGLES:
- - -90
- 0
- 90
ASPECT_RATIOS:
- - 0.5
- 1.0
- 2.0
NAME: DefaultAnchorGenerator
OFFSET: 0.0
SIZES:
- - 32
- 64
- 128
- 256
- 512
BACKBONE:
FREEZE_AT: 2
NAME: build_p67_resnet_fpn_backbone
BIFPN:
NORM: GN
NUM_BIFPN: 6
NUM_LEVELS: 5
OUT_CHANNELS: 160
SEPARABLE_CONV: false
CENTERNET:
AS_PROPOSAL: false
CENTER_NMS: false
FPN_STRIDES:
- 8
- 16
- 32
- 64
- 128
GHM_BINS: 10
GHM_LOSS_WEIGHT: 1.0
GHM_MOMENTUM: 0
HM_FOCAL_ALPHA: 0.25
HM_FOCAL_BETA: 4
HM_MIN_OVERLAP: 0.8
IGNORE_HIGH_FP: -1.0
INFERENCE_TH: 0.05
IN_FEATURES:
- p3
- p4
- p5
- p6
- p7
LOC_LOSS_TYPE: giou
LOSS_GAMMA: 2.0
MIN_RADIUS: 4
MORE_POS: false
MORE_POS_THRESH: 0.2
MORE_POS_TOPK: 9
NEG_WEIGHT: 1.0
NMS_TH_TEST: 0.6
NMS_TH_TRAIN: 0.6
NORM: GN
NOT_NMS: false
NOT_NORM_REG: true
NUM_BOX_CONVS: 4
NUM_CLASSES: 3
NUM_CLS_CONVS: 4
NUM_SHARE_CONVS: 0
ONLY_PROPOSAL: false
POST_NMS_TOPK_TEST: 100
POST_NMS_TOPK_TRAIN: 100
POS_WEIGHT: 1.0
PRE_NMS_TOPK_TEST: 1000
PRE_NMS_TOPK_TRAIN: 1000
PRIOR_PROB: 0.01
PROPOSAL_LOSS_TYPE: focal loss
REG_WEIGHT: 2.0
SIGMOID_CLAMP: 0.0001
SOI:
- - 0
- 80
- - 64
- 160
- - 128
- 320
- - 256
- 640
- - 512
- 10000000
USE_DEFORMABLE: false
WITH_AGN_HM: false
DEVICE: cuda
DLA:
DLAUP_IN_FEATURES:
- dla3
- dla4
- dla5
DLAUP_NODE: conv
MS_OUTPUT: false
NORM: BN
NUM_LAYERS: 34
OUT_FEATURES:
- dla2
USE_DLA_UP: true
DYHEAD:
CHANNELS: 256
NUM_CONVS: 6
FPN:
FUSE_TYPE: sum
IN_FEATURES:
- res3
- res4
- res5
NORM: ''
OUT_CHANNELS: 256
KEYPOINT_ON: false
LOAD_PROPOSALS: false
MASK_ON: false
META_ARCHITECTURE: GeneralizedRCNN
OURNET:
AS_PROPOSAL: false
CENTER_NMS: false
FPN_STRIDES:
- 8
- 16
- 32
- 64
- 128
GHM_BINS: 10
GHM_LOSS_WEIGHT: 1.0
GHM_MOMENTUM: 0
HM_FOCAL_ALPHA: 0.25
HM_FOCAL_BETA: 4
HM_MIN_OVERLAP: 0.8
IGNORE_HIGH_FP: 0.85
INFERENCE_TH: 0.0001
IN_FEATURES:
- p3
- p4
- p5
- p6
- p7
LOC_LOSS_TYPE: giou
LOSS_GAMMA: 2.0
MIN_RADIUS: 4
MORE_POS: false
MORE_POS_THRESH: 0.2
MORE_POS_TOPK: 9
NEG_WEIGHT: 0.5
NMS_TH_TEST: 0.9
NMS_TH_TRAIN: 0.9
NORM: GN
NOT_NMS: false
NOT_NORM_REG: true
NUM_BOX_CONVS: 4
NUM_CLASSES: 3
NUM_CLS_CONVS: 4
NUM_SHARE_CONVS: 0
ONLY_PROPOSAL: true
POST_NMS_TOPK_TEST: 256
POST_NMS_TOPK_TRAIN: 2000
POS_WEIGHT: 0.5
PRE_NMS_TOPK_TEST: 1000
PRE_NMS_TOPK_TRAIN: 4000
PRIOR_PROB: 0.01
PROPOSAL_LOSS_TYPE: focal loss
REG_WEIGHT: 1.0
SIGMOID_CLAMP: 0.0001
SOI:
- - 0
- 80
- - 64
- 160
- - 128
- 320
- - 256
- 640
- - 512
- 10000000
USE_DEFORMABLE: true
WITH_AGN_HM: true
PANOPTIC_FPN:
COMBINE:
ENABLED: true
INSTANCES_CONFIDENCE_THRESH: 0.5
OVERLAP_THRESH: 0.5
STUFF_AREA_LIMIT: 4096
INSTANCE_LOSS_WEIGHT: 1.0
PIXEL_MEAN:
- 103.53
- 116.28
- 123.675
PIXEL_STD:
- 1.0
- 1.0
- 1.0
PROPOSAL_GENERATOR:
MIN_SIZE: 0
NAME: OurNet
RESNETS:
DEFORM_MODULATED: true
DEFORM_NUM_GROUPS: 1
DEFORM_ON_PER_STAGE:
- false
- false
- true
- true
DEPTH: 101
NORM: FrozenBN
NUM_GROUPS: 1
OUT_FEATURES:
- res3
- res4
- res5
RES2_OUT_CHANNELS: 256
RES5_DILATION: 1
STEM_OUT_CHANNELS: 64
STRIDE_IN_1X1: true
WIDTH_PER_GROUP: 64
RETINANET:
BBOX_REG_LOSS_TYPE: smooth_l1
BBOX_REG_WEIGHTS: &id001
- 1.0
- 1.0
- 1.0
- 1.0
FOCAL_LOSS_ALPHA: 0.25
FOCAL_LOSS_GAMMA: 2.0
IN_FEATURES:
- p3
- p4
- p5
- p6
- p7
IOU_LABELS:
- 0
- -1
- 1
IOU_THRESHOLDS:
- 0.4
- 0.5
NMS_THRESH_TEST: 0.5
NORM: ''
NUM_CLASSES: 80
NUM_CONVS: 4
PRIOR_PROB: 0.01
SCORE_THRESH_TEST: 0.05
SMOOTH_L1_LOSS_BETA: 0.1
TOPK_CANDIDATES_TEST: 1000
ROI_BOX_CASCADE_HEAD:
BBOX_REG_WEIGHTS:
- - 10.0
- 10.0
- 5.0
- 5.0
- - 20.0
- 20.0
- 10.0
- 10.0
- - 30.0
- 30.0
- 15.0
- 15.0
IOUS:
- 0.6
- 0.7
- 0.8
ROI_BOX_HEAD:
BBOX_REG_LOSS_TYPE: smooth_l1
BBOX_REG_LOSS_WEIGHT: 1.0
BBOX_REG_WEIGHTS:
- 10.0
- 10.0
- 5.0
- 5.0
CAT_FREQ_PATH: datasets/lvis/lvis_v1_train_cat_info.json
CLS_AGNOSTIC_BBOX_REG: true
CONV_DIM: 256
EQL_FREQ_CAT: 200
FC_DIM: 1024
FED_LOSS_FREQ_WEIGHT: 0.5
FED_LOSS_NUM_CAT: 50
MULT_PROPOSAL_SCORE: true
NAME: FastRCNNConvFCHead
NORM: ''
NUM_CONV: 0
NUM_FC: 2
POOLER_RESOLUTION: 7
POOLER_SAMPLING_RATIO: 0
POOLER_TYPE: ROIAlignV2
PRIOR_PROB: 0.01
SMOOTH_L1_BETA: 0.0
TRAIN_ON_PRED_BOXES: false
USE_EQL_LOSS: false
USE_FED_LOSS: false
USE_IACS: false
USE_SIGMOID_CE: false
ROI_HEADS:
BATCH_SIZE_PER_IMAGE: 512
IN_FEATURES:
- p3
- p4
- p5
- p6
- p7
IOU_LABELS:
- 0
- 1
IOU_THRESHOLDS:
- 0.6
NAME: CustomCascadeROIHeads
NMS_THRESH_TEST: 0.7
NUM_CLASSES: 3
POSITIVE_FRACTION: 0.25
PROPOSAL_APPEND_GT: true
SCORE_THRESH_TEST: 0.05
ROI_KEYPOINT_HEAD:
CONV_DIMS:
- 512
- 512
- 512
- 512
- 512
- 512
- 512
- 512
LOSS_WEIGHT: 1.0
MIN_KEYPOINTS_PER_IMAGE: 1
NAME: KRCNNConvDeconvUpsampleHead
NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
NUM_KEYPOINTS: 17
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 0
POOLER_TYPE: ROIAlignV2
ROI_MASK_HEAD:
CLS_AGNOSTIC_MASK: false
CONV_DIM: 256
NAME: MaskRCNNConvUpsampleHead
NORM: ''
NUM_CONV: 0
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 0
POOLER_TYPE: ROIAlignV2
RPN:
BATCH_SIZE_PER_IMAGE: 256
BBOX_REG_LOSS_TYPE: smooth_l1
BBOX_REG_LOSS_WEIGHT: 1.0
BBOX_REG_WEIGHTS: *id001
BOUNDARY_THRESH: -1
CONV_DIMS:
- -1
HEAD_NAME: StandardRPNHead
IN_FEATURES:
- res4
IOU_LABELS:
- 0
- -1
- 1
IOU_THRESHOLDS:
- 0.3
- 0.7
LOSS_WEIGHT: 1.0
NMS_THRESH: 0.7
POSITIVE_FRACTION: 0.5
POST_NMS_TOPK_TEST: 1000
POST_NMS_TOPK_TRAIN: 2000
PRE_NMS_TOPK_TEST: 6000
PRE_NMS_TOPK_TRAIN: 12000
SMOOTH_L1_BETA: 0.0
SEM_SEG_HEAD:
COMMON_STRIDE: 4
CONVS_DIM: 128
IGNORE_VALUE: 255
IN_FEATURES:
- p2
- p3
- p4
- p5
LOSS_WEIGHT: 1.0
NAME: SemSegFPNHead
NORM: GN
NUM_CLASSES: 54
WEIGHTS: D:\MyFile\dataset\model\processed+aerial_processes\OurNet_R101_DCN\model_0069499.pth
OUTPUT_DIR: ./output/OurNet/OurNet_R101_DCN
SAVE_DEBUG: false
SAVE_PTH: false
SEED: -1
SOLVER:
AMP:
ENABLED: false
BASE_LR: 0.02
BASE_LR_END: 0.0
BIAS_LR_FACTOR: 1.0
CHECKPOINT_PERIOD: 500
CLIP_GRADIENTS:
CLIP_TYPE: value
CLIP_VALUE: 1.0
ENABLED: true
NORM_TYPE: 2.0
GAMMA: 0.1
IMS_PER_BATCH: 1
LR_SCHEDULER_NAME: WarmupMultiStepLR
MAX_ITER: 180000
MOMENTUM: 0.9
NESTEROV: false
REFERENCE_WORLD_SIZE: 0
RESET_ITER: false
STEPS:
- 60000
- 80000
TRAIN_ITER: -1
WARMUP_FACTOR: 0.00025
WARMUP_ITERS: 4000
WARMUP_METHOD: linear
WEIGHT_DECAY: 0.0001
WEIGHT_DECAY_BIAS: null
WEIGHT_DECAY_NORM: 0.0
TEST:
AUG:
ENABLED: false
FLIP: true
MAX_SIZE: 4000
MIN_SIZES:
- 400
- 500
- 600
- 700
- 800
- 900
- 1000
- 1100
- 1200
DETECTIONS_PER_IMAGE: 100
EVAL_PERIOD: 0
EXPECTED_RESULTS: []
KEYPOINT_OKS_SIGMAS: []
PRECISE_BN:
ENABLED: false
NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 0
VIS_THRESH: 0.3
[03/19 20:45:13 detectron2]: Full config saved to ./output/OurNet/OurNet_R101_DCN\config.yaml
[03/19 20:45:13 d2.utils.env]: Using a generated random seed 13956036
[03/19 20:45:15 detectron2]: Model:
GeneralizedRCNN(
(backbone): FPN(
(fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(top_block): LastLevelP6P7_P5(
(p6): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(p7): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
(bottom_up): 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)
)
)
(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)
)
(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(
(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(
(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)
)
(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(
(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(
(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(
(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): DeformBottleneckBlock(
(shortcut): Conv2d(
512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv1): Conv2d(
512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(6): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(7): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(8): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(9): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(10): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(11): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(12): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(13): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(14): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(15): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(16): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(17): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(18): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(19): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(20): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(21): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
(22): DeformBottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2_offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(shortcut): Conv2d(
1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv1): Conv2d(
1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2_offset): Conv2d(512, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=512, out_channels=512, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2_offset): Conv2d(512, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=512, out_channels=512, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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): DeformBottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2_offset): Conv2d(512, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): ModulatedDeformConv(
in_channels=512, out_channels=512, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=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)
)
)
)
)
)
(proposal_generator): OurNet(
(iou_loss): IOULoss()
(ournet_head): OurNetHead(
(cls_tower): Sequential()
(bbox_tower): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): GroupNorm(32, 256, eps=1e-05, affine=True)
(2): ReLU(inplace=True)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): GroupNorm(32, 256, eps=1e-05, affine=True)
(5): ReLU(inplace=True)
(6): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): GroupNorm(32, 256, eps=1e-05, affine=True)
(8): ReLU(inplace=True)
(9): DFConv2d(
(offset): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv): ModulatedDeformConv(in_channels=256, out_channels=256, kernel_size=(3, 3), stride=1, padding=1, dilation=1, groups=1, deformable_groups=1, bias=True)
)
(10): GroupNorm(32, 256, eps=1e-05, affine=True)
(11): ReLU(inplace=True)
)
(share_tower): Sequential()
(offset): Conv2d(256, 18, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(reppoints_dconv): DeformConv(in_channels=256, out_channels=256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), dilation=(1, 1), groups=1, deformable_groups=1, bias=False)
(bbox_pred): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(scales): ModuleList(
(0): Scale()
(1): Scale()
(2): Scale()
(3): Scale()
(4): Scale()
)
(relu): ReLU(inplace=True)
(agn_hm): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(roi_heads): CustomCascadeROIHeads(
(box_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(7, 7), spatial_scale=0.015625, sampling_ratio=0, aligned=True)
(4): ROIAlign(output_size=(7, 7), spatial_scale=0.0078125, sampling_ratio=0, aligned=True)
)
)
(box_head): ModuleList(
(0): FastRCNNConvFCHead(
(flatten): Flatten(start_dim=1, end_dim=-1)
(fc1): Linear(in_features=12544, out_features=1024, bias=True)
(fc_relu1): ReLU()
(fc2): Linear(in_features=1024, out_features=1024, bias=True)
(fc_relu2): ReLU()
)
(1): FastRCNNConvFCHead(
(flatten): Flatten(start_dim=1, end_dim=-1)
(fc1): Linear(in_features=12544, out_features=1024, bias=True)
(fc_relu1): ReLU()
(fc2): Linear(in_features=1024, out_features=1024, bias=True)
(fc_relu2): ReLU()
)
(2): FastRCNNConvFCHead(
(flatten): Flatten(start_dim=1, end_dim=-1)
(fc1): Linear(in_features=12544, out_features=1024, bias=True)
(fc_relu1): ReLU()
(fc2): Linear(in_features=1024, out_features=1024, bias=True)
(fc_relu2): ReLU()
)
)
(box_predictor): ModuleList(
(0): CustomFastRCNNOutputLayers(
(cls_score): Linear(in_features=1024, out_features=4, bias=True)
(bbox_pred): Linear(in_features=1024, out_features=4, bias=True)
)
(1): CustomFastRCNNOutputLayers(
(cls_score): Linear(in_features=1024, out_features=4, bias=True)
(bbox_pred): Linear(in_features=1024, out_features=4, bias=True)
)
(2): CustomFastRCNNOutputLayers(
(cls_score): Linear(in_features=1024, out_features=4, bias=True)
(bbox_pred): Linear(in_features=1024, out_features=4, bias=True)
)
)
)
)
[03/19 20:45:15 fvcore.common.checkpoint]: [Checkpointer] Loading from D:\MyFile\dataset\model\processed+aerial_processes\OurNet_R101_DCN\model_0069499.pth ...
WARNING [03/19 20:45:15 fvcore.common.checkpoint]: Some model parameters or buffers are not found in the checkpoint:
proposal_generator.ournet_head.bbox_tower.9.conv.{bias, weight}
proposal_generator.ournet_head.bbox_tower.9.offset.{bias, weight}
WARNING [03/19 20:45:15 fvcore.common.checkpoint]: The checkpoint state_dict contains keys that are not used by the model:
proposal_generator.ournet_head.bbox_tower.9.{bias, weight}
[03/19 20:45:15 d2.data.datasets.coco]: Loaded 150 images in COCO format from D:\MyFile\dataset\detection\datasets\test\annotations_ori.json
[03/19 20:45:15 d2.data.build]: Distribution of instances among all 3 categories:
| category | #instances | category | #instances | category | #instances |
|:----------:|:-------------|:----------:|:-------------|:----------:|:-------------|
| digger | 41 | motocrane | 196 | towercrane | 49 |
| | | | | | |
| total | 286 | | | | |
[03/19 20:45:15 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(1200, 1200), max_size=3200, sample_style='choice')]
[03/19 20:45:15 d2.data.common]: Serializing 150 elements to byte tensors and concatenating them all ...
[03/19 20:45:15 d2.data.common]: Serialized dataset takes 0.05 MiB
WARNING [03/19 20:45:15 d2.evaluation.coco_evaluation]: COCO Evaluator instantiated using config, this is deprecated behavior. Please pass in explicit arguments instead.
[03/19 20:45:15 d2.evaluation.evaluator]: Start inference on 150 batches
D:\MyFile\tool\Anaconda\lib\site-packages\torch\functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered inter
nally at ..\aten\src\ATen\native\TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
[03/19 20:45:30 d2.evaluation.evaluator]: Inference done 11/150. Dataloading: 0.0007 s/iter. Inference: 0.3719 s/iter. Eval: 0.0003 s/iter. Total: 0.3729 s/iter. ETA=0:00:51
[03/19 20:45:36 d2.evaluation.evaluator]: Inference done 26/150. Dataloading: 0.0008 s/iter. Inference: 0.3555 s/iter. Eval: 0.0003 s/iter. Total: 0.3568 s/iter. ETA=0:00:44
[03/19 20:45:41 d2.evaluation.evaluator]: Inference done 41/150. Dataloading: 0.0008 s/iter. Inference: 0.3552 s/iter. Eval: 0.0003 s/iter. Total: 0.3564 s/iter. ETA=0:00:38
[03/19 20:45:46 d2.evaluation.evaluator]: Inference done 55/150. Dataloading: 0.0009 s/iter. Inference: 0.3556 s/iter. Eval: 0.0003 s/iter. Total: 0.3569 s/iter. ETA=0:00:33
[03/19 20:45:51 d2.evaluation.evaluator]: Inference done 70/150. Dataloading: 0.0008 s/iter. Inference: 0.3544 s/iter. Eval: 0.0003 s/iter. Total: 0.3557 s/iter. ETA=0:00:28
[03/19 20:45:56 d2.evaluation.evaluator]: Inference done 84/150. Dataloading: 0.0008 s/iter. Inference: 0.3553 s/iter. Eval: 0.0003 s/iter. Total: 0.3565 s/iter. ETA=0:00:23
[03/19 20:46:01 d2.evaluation.evaluator]: Inference done 96/150. Dataloading: 0.0009 s/iter. Inference: 0.3643 s/iter. Eval: 0.0003 s/iter. Total: 0.3656 s/iter. ETA=0:00:19
[03/19 20:46:07 d2.evaluation.evaluator]: Inference done 110/150. Dataloading: 0.0010 s/iter. Inference: 0.3653 s/iter. Eval: 0.0003 s/iter. Total: 0.3670 s/iter. ETA=0:00:14
[03/19 20:46:12 d2.evaluation.evaluator]: Inference done 124/150. Dataloading: 0.0010 s/iter. Inference: 0.3659 s/iter. Eval: 0.0003 s/iter. Total: 0.3675 s/iter. ETA=0:00:09
[03/19 20:46:17 d2.evaluation.evaluator]: Inference done 138/150. Dataloading: 0.0010 s/iter. Inference: 0.3665 s/iter. Eval: 0.0003 s/iter. Total: 0.3681 s/iter. ETA=0:00:04
[03/19 20:46:22 d2.evaluation.evaluator]: Total inference time: 0:00:54.190565 (0.373728 s / iter per device, on 1 devices)
[03/19 20:46:22 d2.evaluation.evaluator]: Total inference pure compute time: 0:00:53 (0.369442 s / iter per device, on 1 devices)
[03/19 20:46:22 d2.evaluation.coco_evaluation]: Preparing results for COCO format ...
[03/19 20:46:22 d2.evaluation.coco_evaluation]: Saving results to ./output/OurNet/OurNet_R101_DCN\inference_test\coco_instances_results.json
[03/19 20:46:22 d2.evaluation.coco_evaluation]: Evaluating predictions with unofficial COCO API...
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
[03/19 20:46:22 d2.evaluation.fast_eval_api]: Evaluate annotation type *bbox*
[03/19 20:46:22 d2.evaluation.fast_eval_api]: COCOeval_opt.evaluate() finished in 0.05 seconds.
[03/19 20:46:22 d2.evaluation.fast_eval_api]: Accumulating evaluation results...
[03/19 20:46:22 d2.evaluation.fast_eval_api]: COCOeval_opt.accumulate() finished in 0.01 seconds.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.010
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.021
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.010
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.012
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.013
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.015
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.015
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.020
[03/19 20:46:22 d2.evaluation.coco_evaluation]: Evaluation results for bbox:
| AP | AP50 | AP75 | APs | APm | APl |
|:-----:|:------:|:------:|:-----:|:-----:|:-----:|
| 1.039 | 2.132 | 0.990 | 0.000 | 0.000 | 1.226 |
[03/19 20:46:22 d2.evaluation.coco_evaluation]: Per-category bbox AP:
| category | AP | category | AP | category | AP |
|:-----------|:------|:-----------|:------|:-----------|:------|
| digger | 0.000 | motocrane | 2.673 | towercrane | 0.446 |
[03/19 20:46:22 detectron2]: Evaluation results for test in csv format:
[03/19 20:46:22 d2.evaluation.testing]: copypaste: Task: bbox
[03/19 20:46:22 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl
[03/19 20:46:22 d2.evaluation.testing]: copypaste: 1.0395,2.1322,0.9901,0.0000,0.0000,1.2261