Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom

When I run the train.py with the config oriented_reppoints_r50_fpn_1x_dota_le135.py, it reports the error, RuntimeError: CUDA error: invalid configuration argument #563

Closed
JinqingZhengTju opened this issue Oct 22, 2022 · 3 comments
Closed

When I run the train.py with the config oriented_reppoints_r50_fpn_1x_dota_le135.py, it reports the error, RuntimeError: CUDA error: invalid configuration argument #563

JinqingZhengTju opened this issue Oct 22, 2022 · 3 comments

Comments

@JinqingZhengTju
Copy link

Thanks for your error report and we appreciate it a lot.

Checklist

  1. I have searched related issues but cannot get the expected help.
  2. I have read the FAQ documentation but cannot get the expected help.
  3. The bug has not been fixed in the latest version.

Describe the bug
A clear and concise description of what the bug is.

Reproduction

  1. What command or script did you run?
A placeholder for the command.
  1. Did you make any modifications on the code or config? Did you understand what you have modified?
  2. What dataset did you use?

Environment

  1. Please run python mmrotate/utils/collect_env.py to collect necessary environment information and paste it here.
    sys.platform: linux
    Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0]
    CUDA available: True
    GPU 0: NVIDIA GeForce RTX 3090
    CUDA_HOME: /usr/local/cuda
    NVCC: Cuda compilation tools, release 11.3, V11.3.109
    GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
    PyTorch: 1.10.2
    PyTorch compiling details: PyTorch built with:
  • GCC 7.3
  • 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 v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • LAPACK is enabled (usually provided by MKL)
  • NNPACK is enabled
  • CPU capability usage: AVX512
  • CUDA Runtime 11.3
  • 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 8.2
  • Magma 2.5.2
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -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 -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-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 -Wno-stringop-overflow, 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_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,

TorchVision: 0.11.3
OpenCV: 4.6.0
MMCV: 1.6.0
MMCV Compiler: GCC 9.4
MMCV CUDA Compiler: 11.3
MMRotate: 0.3.2+c62f148
3. You may add addition that may be helpful for locating the problem, such as

  • How you installed PyTorch [e.g., pip, conda, source]
  • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback
If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix
If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!
@JinqingZhengTju
Copy link
Author

Thanks for your error report and we appreciate it a lot.

Checklist

  1. I have searched related issues but cannot get the expected help.
  2. I have read the FAQ documentation but cannot get the expected help.
  3. The bug has not been fixed in the latest version.

Describe the bug A clear and concise description of what the bug is.

Reproduction

  1. What command or script did you run?
A placeholder for the command.
  1. Did you make any modifications on the code or config? Did you understand what you have modified?
  2. What dataset did you use?

Environment

  1. Please run python mmrotate/utils/collect_env.py to collect necessary environment information and paste it here.
    sys.platform: linux
    Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0]
    CUDA available: True
    GPU 0: NVIDIA GeForce RTX 3090
    CUDA_HOME: /usr/local/cuda
    NVCC: Cuda compilation tools, release 11.3, V11.3.109
    GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
    PyTorch: 1.10.2
    PyTorch compiling details: PyTorch built with:
  • GCC 7.3
  • 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 v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • LAPACK is enabled (usually provided by MKL)
  • NNPACK is enabled
  • CPU capability usage: AVX512
  • CUDA Runtime 11.3
  • 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 8.2
  • Magma 2.5.2
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -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 -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-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 -Wno-stringop-overflow, 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_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,

TorchVision: 0.11.3 OpenCV: 4.6.0 MMCV: 1.6.0 MMCV Compiler: GCC 9.4 MMCV CUDA Compiler: 11.3 MMRotate: 0.3.2+c62f148 3. You may add addition that may be helpful for locating the problem, such as

  • How you installed PyTorch [e.g., pip, conda, source]
  • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

I don't know why the oriented reppoints and rotated reppoints have this error. The error is reported as follows:
2022-10-29 22:43:20,313 - mmrotate - INFO - workflow: [('train', 1)], max: 12 epochs
2022-10-29 22:43:20,313 - mmrotate - INFO - Checkpoints will be saved to /media/zjq/Data/Ubuntu_Project/svd/mmrotate/work_dirs/DOTA/oriented_reppoints by HardDiskBackend.
/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1659484809535/work/aten/src/ATen/native/TensorShape.cpp:2894.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/torch/nn/functional.py:4216: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details.
"Default grid_sample and affine_grid behavior has changed "
Traceback (most recent call last):
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/tools/train/train_oriented_reppoints_dota.py", line 209, in
main()
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/tools/train/train_oriented_reppoints_dota.py", line 205, in main
meta=meta)
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/apis/train.py", line 141, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 53, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 32, in run_iter
**kwargs)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/parallel/data_parallel.py", line 77, in train_step
return self.module.train_step(*inputs[0], **kwargs[0])
File "/media/zjq/Data/Ubuntu_Project/svd/mmdetection/mmdet/models/detectors/base.py", line 248, in train_step
losses = self(**data)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 116, in new_func
return old_func(*args, **kwargs)
File "/media/zjq/Data/Ubuntu_Project/svd/mmdetection/mmdet/models/detectors/base.py", line 172, in forward
return self.forward_train(img, img_metas, *kwargs)
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/models/detectors/single_stage.py", line 82, in forward_train
gt_labels, gt_bboxes_ignore)
File "/media/zjq/Data/Ubuntu_Project/svd/mmdetection/mmdet/models/dense_heads/base_dense_head.py", line 335, in forward_train
losses = self.loss(loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/models/dense_heads/oriented_reppoints_head.py", line 925, in loss
label_channels=label_channels)
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/models/dense_heads/oriented_reppoints_head.py", line 807, in get_targets
unmap_outputs=unmap_outputs)
File "/media/zjq/Data/Ubuntu_Project/svd/mmdetection/mmdet/core/utils/misc.py", line 30, in multi_apply
return tuple(map(list, zip(map_results)))
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/models/dense_heads/oriented_reppoints_head.py", line 677, in _point_target_single
None if self.sampling else gt_labels)
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/core/bbox/assigners/max_convex_iou_assigner.py", line 102, in assign
overlaps = self.convex_overlaps(gt_rbboxes, points)
File "/media/zjq/Data/Ubuntu_Project/svd/mmrotate/mmrotate/core/bbox/assigners/max_convex_iou_assigner.py", line 215, in convex_overlaps
overlaps = convex_iou(points, gt_rbboxes)
File "/home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/ops/convex_iou.py", line 51, in convex_iou
ext_module.convex_iou(pointsets, polygons, ious)
RuntimeError: CUDA error: invalid configuration argument
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Exception raised from ConvexIoUCUDAKernelLauncher at /tmp/mmcv/mmcv/ops/csrc/pytorch/cuda/convex_iou.cu:22 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x57 (0x7f679c82f497 in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #1: c10::CUDAError::Error(c10::SourceLocation, std::string) + 0x30 (0x7f675bd74024 in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #2: ConvexIoUCUDAKernelLauncher(at::Tensor, at::Tensor, at::Tensor) + 0x1be (0x7f675bd9cd6f in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #3: convex_iou_cuda(at::Tensor, at::Tensor, at::Tensor) + 0x69 (0x7f675bdad309 in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #4: auto Dispatch<DeviceRegistry<void ()(at::Tensor, at::Tensor, at::Tensor), &(convex_iou_impl(at::Tensor, at::Tensor, at::Tensor))>, at::Tensor const&, at::Tensor const&, at::Tensor&>(DeviceRegistry<void ()(at::Tensor, at::Tensor, at::Tensor), &(convex_iou_impl(at::Tensor, at::Tensor, at::Tensor))> const&, char const, at::Tensor const&, at::Tensor const&, at::Tensor&) + 0xea (0x7f675bd14e8a in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #5: convex_iou(at::Tensor, at::Tensor, at::Tensor) + 0x69 (0x7f675bd14a69 in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #6: + 0x2a1ce1 (0x7f675bf17ce1 in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #7: + 0x2b4ba1 (0x7f675bf2aba1 in /home/zjq/anaconda3/envs/svd/lib/python3.7/site-packages/mmcv/_ext.cpython-37m-x86_64-linux-gnu.so)
frame #8: _PyMethodDef_RawFastCallKeywords + 0x237 (0x4bb4e7 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #9: /home/zjq/anaconda3/envs/svd/bin/python() [0x4baf40]
frame #10: _PyEval_EvalFrameDefault + 0x469a (0x4b793a in /home/zjq/anaconda3/envs/svd/bin/python)
frame #11: _PyFunction_FastCallKeywords + 0x106 (0x4c61f6 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #12: /home/zjq/anaconda3/envs/svd/bin/python() [0x4bae2f]
frame #13: _PyEval_EvalFrameDefault + 0x971 (0x4b3c11 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #14: _PyFunction_FastCallKeywords + 0x106 (0x4c61f6 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #15: /home/zjq/anaconda3/envs/svd/bin/python() [0x4bae2f]
frame #16: _PyEval_EvalFrameDefault + 0xa9e (0x4b3d3e in /home/zjq/anaconda3/envs/svd/bin/python)
frame #17: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #18: _PyFunction_FastCallKeywords + 0x29c (0x4c638c in /home/zjq/anaconda3/envs/svd/bin/python)
frame #19: /home/zjq/anaconda3/envs/svd/bin/python() [0x4bae2f]
frame #20: _PyEval_EvalFrameDefault + 0xa9e (0x4b3d3e in /home/zjq/anaconda3/envs/svd/bin/python)
frame #21: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #22: _PyFunction_FastCallDict + 0x2d6 (0x4cd006 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #23: /home/zjq/anaconda3/envs/svd/bin/python() [0x4d5ec0]
frame #24: PyObject_Call + 0x51 (0x4d35a1 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #25: /home/zjq/anaconda3/envs/svd/bin/python() [0x580e87]
frame #26: /home/zjq/anaconda3/envs/svd/bin/python() [0x51b401]
frame #27: PySequence_Tuple + 0x16b (0x4a30cb in /home/zjq/anaconda3/envs/svd/bin/python)
frame #28: _PyEval_EvalFrameDefault + 0x570f (0x4b89af in /home/zjq/anaconda3/envs/svd/bin/python)
frame #29: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #30: _PyFunction_FastCallKeywords + 0x29c (0x4c638c in /home/zjq/anaconda3/envs/svd/bin/python)
frame #31: /home/zjq/anaconda3/envs/svd/bin/python() [0x4bae2f]
frame #32: _PyEval_EvalFrameDefault + 0x15d2 (0x4b4872 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #33: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #34: _PyFunction_FastCallKeywords + 0x29c (0x4c638c in /home/zjq/anaconda3/envs/svd/bin/python)
frame #35: /home/zjq/anaconda3/envs/svd/bin/python() [0x4bae2f]
frame #36: _PyEval_EvalFrameDefault + 0x15d2 (0x4b4872 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #37: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #38: _PyFunction_FastCallDict + 0x2d6 (0x4cd006 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #39: /home/zjq/anaconda3/envs/svd/bin/python() [0x4d5ec0]
frame #40: PyObject_Call + 0x51 (0x4d35a1 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #41: _PyEval_EvalFrameDefault + 0x1ea8 (0x4b5148 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #42: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #43: _PyFunction_FastCallKeywords + 0x29c (0x4c638c in /home/zjq/anaconda3/envs/svd/bin/python)
frame #44: /home/zjq/anaconda3/envs/svd/bin/python() [0x4bae2f]
frame #45: _PyEval_EvalFrameDefault + 0x469a (0x4b793a in /home/zjq/anaconda3/envs/svd/bin/python)
frame #46: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #47: _PyFunction_FastCallDict + 0x2d6 (0x4cd006 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #48: /home/zjq/anaconda3/envs/svd/bin/python() [0x4d5ec0]
frame #49: PyObject_Call + 0x51 (0x4d35a1 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #50: _PyEval_EvalFrameDefault + 0x1ea8 (0x4b5148 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #51: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #52: _PyFunction_FastCallDict + 0x2d6 (0x4cd006 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #53: _PyEval_EvalFrameDefault + 0x1ea8 (0x4b5148 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #54: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #55: _PyFunction_FastCallDict + 0x2d6 (0x4cd006 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #56: /home/zjq/anaconda3/envs/svd/bin/python() [0x4d5ec0]
frame #57: PyObject_Call + 0x51 (0x4d35a1 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #58: _PyEval_EvalFrameDefault + 0x1ea8 (0x4b5148 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #59: _PyEval_EvalCodeWithName + 0x201 (0x4b2041 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #60: _PyFunction_FastCallDict + 0x2d6 (0x4cd006 in /home/zjq/anaconda3/envs/svd/bin/python)
frame #61: _PyObject_Call_Prepend + 0x6e (0x4d1dfe in /home/zjq/anaconda3/envs/svd/bin/python)
frame #62: /home/zjq/anaconda3/envs/svd/bin/python() [0x580007]
frame #63: PyObject_Call + 0x51 (0x4d35a1 in /home/zjq/anaconda3/envs/svd/bin/python)

Process finished with exit code 1

@zytx121
Copy link
Collaborator

zytx121 commented Oct 30, 2022

Please check the input of convex_iou. Illegal input causes this error.

Refer to https://github.com/open-mmlab/mmcv/blob/699398ad8697516304a2207ef248bf8d3e6e1b7b/mmcv/ops/convex_iou.py

@JinqingZhengTju
Copy link
Author

Please check the input of convex_iou. Illegal input causes this error.

Refer to https://github.com/open-mmlab/mmcv/blob/699398ad8697516304a2207ef248bf8d3e6e1b7b/mmcv/ops/convex_iou.py

Thanks for your reply. I will check it.

@zytx121 zytx121 closed this as completed Feb 11, 2023
# for free to join this conversation on GitHub. Already have an account? # to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zytx121 @JinqingZhengTju