The test process stuck

[SuhZhang]

I tried to reimplementation Swin-B on COCO, I just git the repository on Github and download the model file through the link in README. But when test the model by: python tools/test.py configs/swin/cascade_mask_rcnn_swin_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py checkpoint/cascade_mask_rcnn_swin_base_patch4_window7.pth --eval bbox segm

Firstly, I think maybe the memory of GPU is not enough, but when the process is running, I use command nvidia-smi:

Seems that all things are right. I don't know what's wrong, hope someone could give me help!!! By the way, I have only modified the code in _./configs/base/datasets/cocoinstance.py and _configs/base/datasets/coco_instancesemantic.py, just the path of COCO dataset.

Here is my environment:

sys.platform: linux Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] CUDA available: True GPU 0: GeForce GTX 1080 Ti CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 10.1, V10.1.243 GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 PyTorch: 1.6.0 PyTorch compiling details: PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 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,

TorchVision: 0.7.0 OpenCV: 4.5.3 MMCV: 1.3.14 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMDetection: 2.11.0+6a979e2

[SuhZhang]

I met the question for I use remote tool in VS Code. but finally I still met the same question as here when I used VNC. Please pay attention to the question through the link, and if anyone has solved the problem, please share any idea. This issue is closed.

[SuhZhang]

I met the question for I use remote tool in VS Code. but finally I still met the same question as here when I used VNC. Please pay attention to the question through the link, and if anyone has solved the problem, please share any idea. This issue is closed.

I have solved the 'embed_dim', 'ape' & 'use_checkpoint' problem referring to here. But I meet the problem in this issue again. I would be appreciate if anyone could give me some suggestions.