Pruning detectron2's Faster R-CNN #4875
Description
Hello,
I am attempting to prune Faster R-CNN which was created by detectron2, based on the pruning speed_up tutorial.
When I run the code, the program seem to be stuck in the "Dectected conv prune dim" 0" line (as can be seen from console output pasted below). Ad a sanity check, I run the code on torchvision.models.resnet50 model and it worked.
The code is available here: nni_pruning_issue.txt
Console output
ssh://root@localhost:2222/opt/conda/bin/python -u /workspace/detectron2_proj/tools/for_nni_issues.py
torch version 1.11.0a0+b6df043
detectron2 version 0.6
nni version 2.7
[05/19 13:41:58 detectron2]: Rank of current process: 0. World size: 1
[05/19 13:41:58 detectron2]: Environment info:
sys.platform linux
Python 3.8.12 | packaged by conda-forge | (default, Oct 12 2021, 21:59:51) [GCC 9.4.0]
numpy 1.21.4
detectron2 0.6 @/workspace/detectron2_proj/detectron2
Compiler GCC 9.3
CUDA compiler CUDA 11.5
detectron2 arch flags 5.2, 6.0, 6.1, 7.0, 7.5, 8.0, 8.6
DETECTRON2_ENV_MODULE
PyTorch 1.11.0a0+b6df043 @/opt/conda/lib/python3.8/site-packages/torch
PyTorch debug build False
GPU available Yes
GPU 0,1 GeForce RTX 2080 Ti (arch=7.5)
Driver version 460.91.03
CUDA_HOME /usr/local/cuda
Pillow 7.2.0
torchvision 0.11.0a0 @/opt/conda/lib/python3.8/site-packages/torchvision
torchvision arch flags 5.2, 6.0, 6.1, 7.0, 7.5, 8.0, 8.6
fvcore 0.1.5.post20210825
iopath 0.1.9
cv2 4.5.3
PyTorch built with:
- GCC 9.3
- C++ Version: 201402
- Intel(R) Math Kernel Library Version 2019.0.5 Product Build 20190808 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.2.3 (Git Hash N/A)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX512
- CUDA Runtime 11.5
- NVCC architecture flags: -gencode;arch=compute_52,code=sm_52;-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_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_86,code=compute_86
- CuDNN 8.3
- Magma 2.5.2
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.5, CUDNN_VERSION=8.3.0, CXX_COMPILER=/usr/bin/c++, CXX_FLAGS=-fno-gnu-unique -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -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-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=ON, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,
[05/19 13:41:59 d2.utils.env]: Using a generated random seed 59344232
[05/19 13:42:03 d2.engine.defaults]: Model:
GeneralizedRCNN(
(backbone): FPN(
(fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(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): LastLevelMaxPool()
(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, 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), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
256, 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), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
256, 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), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 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, 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=(2, 2), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
512, 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), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
512, 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), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
512, 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), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 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)
)
(conv1): Conv2d(
512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(4): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(5): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(6): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(7): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(8): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(9): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(10): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(11): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(12): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(13): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(14): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(15): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(16): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(17): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(18): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(19): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(20): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(21): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(22): BottleneckBlock(
(conv1): Conv2d(
1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv2): Conv2d(
1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv3): Conv2d(
1024, 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)
)
(conv1): Conv2d(
1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv2): Conv2d(
2048, 2048, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv3): Conv2d(
2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv2): Conv2d(
2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv3): Conv2d(
2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv2): Conv2d(
2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv3): Conv2d(
2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
)
)
)
(proposal_generator): RPN(
(rpn_head): StandardRPNHead(
(conv): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
(activation): ReLU()
)
(objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
(anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
)
(anchor_generator): DefaultAnchorGenerator(
(cell_anchors): BufferList()
)
)
(roi_heads): StandardROIHeads(
(box_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
)
)
(box_head): 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): FastRCNNOutputLayers(
(cls_score): Linear(in_features=1024, out_features=2, bias=True)
(bbox_pred): Linear(in_features=1024, out_features=4, bias=True)
)
)
)
/workspace/detectron2_proj/detectron2/structures/image_list.py:79: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert t.shape[:-2] == tensors[0].shape[:-2], t.shape
/opt/conda/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/pytorch/pytorch/aten/src/ATen/native/TensorShape.cpp:2156.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/workspace/detectron2_proj/detectron2/structures/boxes.py:148: TracerWarning: torch.as_tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect.
tensor = torch.as_tensor(tensor, dtype=torch.float32, device=device)
/workspace/detectron2_proj/detectron2/structures/boxes.py:153: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
/workspace/detectron2_proj/detectron2/modeling/proposal_generator/proposal_utils.py:101: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if not valid_mask.all():
/workspace/detectron2_proj/detectron2/structures/boxes.py:189: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
/workspace/detectron2_proj/detectron2/structures/boxes.py:190: TracerWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
h, w = box_size
/workspace/detectron2_proj/detectron2/layers/nms.py:16: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert boxes.shape[-1] == 4
/workspace/detectron2_proj/detectron2/layers/nms.py:19: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results.
if len(boxes) < 40000:
/workspace/detectron2_proj/detectron2/structures/instances.py:74: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results.
data_len = len(value)
/workspace/detectron2_proj/detectron2/modeling/poolers.py:211: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert len(box_lists) == x[0].size(
/workspace/detectron2_proj/detectron2/layers/roi_align.py:55: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert rois.dim() == 2 and rois.size(1) == 5
/workspace/detectron2_proj/detectron2/modeling/roi_heads/fast_rcnn.py:137: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if not valid_mask.all():
/workspace/detectron2_proj/detectron2/modeling/roi_heads/fast_rcnn.py:142: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
num_bbox_reg_classes = boxes.shape[1] // 4
/workspace/detectron2_proj/detectron2/modeling/roi_heads/fast_rcnn.py:154: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if num_bbox_reg_classes == 1:
[2022-05-19 13:42:08] INFO (nni.compression.pytorch.speedup.compressor/MainThread) start to speedup the model
[2022-05-19 13:42:12] INFO (FixMaskConflict/MainThread) {'model.backbone.fpn_lateral5': 1, 'model.backbone.fpn_output5': 1, 'model.backbone.fpn_lateral4': 1, 'model.backbone.fpn_output4': 1, 'model.backbone.fpn_lateral3': 1, 'model.backbone.fpn_output3': 1, 'model.backbone.fpn_lateral2': 1, 'model.backbone.fpn_output2': 1, 'model.proposal_generator.rpn_head.objectness_logits': 1, 'model.proposal_generator.rpn_head.anchor_deltas': 1}
[2022-05-19 13:42:12] INFO (FixMaskConflict/MainThread) dim0 sparsity: 0.499995
[2022-05-19 13:42:12] INFO (FixMaskConflict/MainThread) dim1 sparsity: 0.000000
[2022-05-19 13:42:12] INFO (FixMaskConflict/MainThread) Dectected conv prune dim" 0
Environment:
- NNI version: 2.7
- Client OS: Ubuntu 18.04
- Python version: Python 3.8.12
- PyTorch/TensorFlow version: 1.11.0a0+b6df043
- Is conda/virtualenv/venv used?: Yes
- Is running in Docker?: nvcr.io/nvidia/pytorch:21.11-py3
Best Regards