search

JialeCao001 / D2Det

D2Det: Towards High Quality Object Detection and Instance Segmentation (CVPR2020)
https://openaccess.thecvf.com/content_CVPR_2020/papers/Cao_D2Det_Towards_High_Quality_Object_Detection_and_Instance_Segmentation_CVPR_2020_paper.pdf
MIT License
297 stars 86 forks source link

RuntimeError: CUDA error: invalid device function #19

Closed CuberrChen closed 4 years ago

CuberrChen commented 4 years ago

hi！I'm trying to learn your work.but when I run the demo.py , the error happened. as you can see, the code can't perfom. my environmental configuration： python=3.7 pytorch=1.4 cuda = 10.0 mmcv=0.4.3

` inds = nms_cuda.nms(dets_th, iou_thr) RuntimeError: CUDA error: invalid device function (launch_kernel at /opt/conda/conda-bld/pytorch_1579022060824/work/aten/src/ATen/native/cuda/Loops.cuh:103) frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x47 (0x7f4a9e223627 in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libc10.so) frame #1: void at::native::gpu_index_kernel<nv_dl_wrapper_t<nv_dl_tag<void (*)(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef), &(void at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef)), 1u>> >(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef, nv_dl_wrapper_t<nv_dl_tag<void (*)(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef), &(void at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef)), 1u>> const&) + 0x78d (0x7f4aaa4fc68d in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #2: + 0x571bf32 (0x7f4aaa4f5f32 in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #3: + 0x571c298 (0x7f4aaa4f6298 in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #4: + 0x16957eb (0x7f4aa646f7eb in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #5: at::native::index(at::Tensor const&, c10::ArrayRef) + 0x47e (0x7f4aa646b5ae in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #6: + 0x1c0155a (0x7f4aa69db55a in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #7: + 0x1c06023 (0x7f4aa69e0023 in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #8: + 0x3820d1a (0x7f4aa85fad1a in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #9: + 0x1c06023 (0x7f4aa69e0023 in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #10: at::Tensor::index(c10::ArrayRef) const + 0x191 (0x7f4ad50ea931 in /home/chenxiangbo/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/lib/libtorch_python.so) frame #11: nms_cuda(at::Tensor, float) + 0x84f (0x7f4a7b0e3bbc in /home/chenxiangbo/D2Det/demo/../mmdet/ops/nms/nms_cuda.cpython-37m-x86_64-linux-gnu.so) frame #12: nms(at::Tensor const&, float) + 0xee (0x7f4a7b0d217e in /home/chenxiangbo/D2Det/demo/../mmdet/ops/nms/nms_cuda.cpython-37m-x86_64-linux-gnu.so) frame #13: + 0x3c75b (0x7f4a7b0e175b in /home/chenxiangbo/D2Det/demo/../mmdet/ops/nms/nms_cuda.cpython-37m-x86_64-linux-gnu.so) frame #14: + 0x38ee0 (0x7f4a7b0ddee0 in /home/chenxiangbo/D2Det/demo/../mmdet/ops/nms/nms_cuda.cpython-37m-x86_64-linux-gnu.so)

`
JialeCao001 commented 4 years ago

@FireflyInwater Hi. Thanks for interest. Please to use pytorch1.1.0.