mmselfsup
mmselfsup copied to clipboard
open-mmlab
[Bug] load VOC07 dataset
Branch
1.x branch (1.x version, such as v1.0.0rc2, or dev-1.x branch)
Prerequisite
- [X] I have searched Issues and Discussions but cannot get the expected help.
- [X] I have read the documentation but cannot get the expected help.
- [X] The bug has not been fixed in the latest version.
Environment
sys.platform: linux Python: 3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0: NVIDIA GeForce RTX 3090 CUDA_HOME: /data/apps/cuda/11.6 NVCC: Cuda compilation tools, release 11.6, V11.6.112 GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) PyTorch: 1.13.0 PyTorch compiling details: PyTorch built with:
- GCC 9.3
- C++ Version: 201402
- Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 11.6
- 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_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
- CuDNN 8.3.2 (built against CUDA 11.5)
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -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 -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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=1.13.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,
TorchVision: 0.14.0 OpenCV: 4.6.0 MMEngine: 0.4.0 MMCV: 2.0.0rc3 MMCV Compiler: GCC 9.3 MMCV CUDA Compiler: 11.6 MMSelfSup: 1.0.0rc5+1e4135a
Describe the bug
I tried to implement downstream task on VOC07 dataset, but there's something wrong with PackSelfSup.
I ran the command
sbatch --gpus=8 tools/benchmarks/classification/svm_voc07/slurm_test_svm_pretrain.sh gpu voc configs/selfsup/orl/stage3/orl_resnet50_8xb64-coslr-800e_coco.py ./orl_r50_coco_ep800.pth feat5
on the slurm cluster.
However, the PackSelfSup mistakenly output with type List[Tuple[Tensor, Tensor, Tensor]], which contradicts the needed List[Tensor]. Actually, Tuple[Tensor, Tensor,Tensor] corresponds to the loaded image's three channels respectively and I don't know why this weird bug happended. As a result, an error raised due to type mismatching
File "/data/run01/scz5891/mmselfsup/mmselfsup/models/utils/data_preprocessor.py", line 60, in
Reproduces the problem - code sample
No response
Reproduces the problem - command or script
sbatch --gpus=1 tools/benchmarks/classification/svm_voc07/slurm_test_svm_pretrain.sh ${PARTITION} ${JOBNAME} \ configs/selfsup/orl/stage3/orl_resnet50_8xb64-coslr-800e_coco.py ./orl_r50_coco_ep800.pth feat5
"configs/selfsup/orl/stage3/orl_resnet50_8xb64-coslr-800e_coco.py" corresponds to ${SELFSUP_CONFIG}, "./orl_r50_coco_ep800.pth" is the pretrained model， and "feat5" means that ${FEATURE_LIST}
Reproduces the problem - error message
Traceback (most recent call last):
File "/data/run01/scz5891/mmselfsup/tools/benchmarks/classification/svm_voc07/extract.py", line 204, in
Additional information
No response
