StevenGrove
from cvpods import _C
ImportError: cannot import name '_C' from 'cvpods' (/home/yuejiutao/Code/RealSR_exp/CDC/modules/LearnableTreeFilterV2/cvpods/init.py)
Did you build the project? Please refer to the build-from-source section. By the way, if you have permission issues, please try to use python setup.py build develop --user.
Did you build the project? Please refer to the build-from-source section. By the way, if you have permission issues, please try to use
python setup.py build develop --user.
Yes , i have built the project ...
Is it because I tried TreeV1
when i build the project ,i meet this problem
`` warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name)) /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/home/yuejiutao/Code/LearnableTreeFilterV2/cvpods/layers/csrc -I/home/yuejiutao/anaconda3/envs/treeV2/lib/python3.7/site-packages/torch/include -I/home/yuejiutao/anaconda3/envs/treeV2/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/yuejiutao/anaconda3/envs/treeV2/lib/python3.7/site-packages/torch/include/TH -I/home/yuejiutao/anaconda3/envs/treeV2/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/yuejiutao/anaconda3/envs/treeV2/include/python3.7m -c /home/yuejiutao/Code/LearnableTreeFilterV2/cvpods/layers/csrc/lars/adaptive_lr_cuda.cu -o build/temp.linux-x86_64-3.7/home/yuejiutao/Code/LearnableTreeFilterV2/cvpods/layers/csrc/lars/adaptive_lr_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14 nvcc fatal : Unsupported gpu architecture 'compute_75' error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1
Is this a normal question？
You could get some help from this issue: https://github.com/facebookresearch/detectron2/issues/149#issuecomment-545793165.
You could get some help from this issue: facebookresearch/detectron2#149 (comment).
Thanks it works...
This project did not use any deformable conv .So it only use pytorch can be use. Those package is rubbish
Hmmm, this repo indeed has nothing to do with the deformable convolutions, but you need to build kernels for the tree filter.