superpixPool
superpixPool copied to clipboard
Superpixel Pooling implemented in PyTorch and Chainer
Cannot compile .cpp to .obj, how should I change the source code? LINK : fatal error LNK1181: cannot open input file“D:\pycharmWorkSpaces\superpixPool-master\pytorch_superpixpool\build\temp.win-amd64-3.6\Release\suppixpool_cuda.obj” error: command 'D:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Community\\VC\\Tools\\MSVC\\14.29.30133\\bin\\HostX64\\x64\\link.exe' failed with...
Error?
I setup the lib by "python setup.py install" and then run "python test_GPUpool.py". And I got an error: ImportError: /home/xidexia/anaconda3/lib/python3.6/site-packages/suppixpool_CUDA-0.0.0-py3.6-linux-x86_64.egg/suppixpool_CUDA.cpython-36m-x86_64-linux-gnu.so: undefined symbol: __cudaPopCallConfiguration
how can i use average suppixpool in GPU, can only max version be implemented here? thanks
How to change your code to run with pytorch1.0? Thank you!
these changes are need to compile the package (I have torch 1.1.0 with cuda 10)
I am running your code, but there is a bug that I can't solve, I hope I can get your help, thank you. RuntimeError: cublas runtime error : resource allocation...
I am able to build setup.py and run test_GPUpool without errors. But gradient check results are always wrong. And I got the following warnings: UserWarning: At least one of the...
Error
Hi,Bermanmaxim, I have setup the lib by "python setup.py install" and the run "python test_GPUpool.py", but finding some error when I run the code: suppixpool_CUDA-0.0.0-py3.6-linux-x86_64.egg/suppixpool_CUDA.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN2at5ErrorC1ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE Could you...