Open wangfei-cs opened 6 years ago
Same here.
/detectorch/lib/cppcuda/build$ ninja [1/4] /usr/local/cuda/bin/nvcc -DTORCH...da.cu -o roi_align_forward_cuda.cuda.o FAILED: roi_align_forward_cuda.cuda.o /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=roialign -I/home/ubuntu/anaconda3/envs/pytorch_p36_2/lib/python3.6/site-packages/torch/lib/include -I/home/ubuntu/anaconda3/envs/pytorch_p36_2/lib/python3.6/site-packages/torch/lib/include/TH -I/home/ubuntu/anaconda3/envs/pytorch_p36_2/lib/python3.6/site-packages/torch/lib/include/THC -I/usr/local/cuda/include -I/home/ubuntu/anaconda3/envs/pytorch_p36_2/include/python3.6m -D_GLIBCXX_USE_CXX11_ABI=0 --compiler-options '-fPIC' -std=c++11 -c /data/repos/detectorch/lib/cppcuda/roi_align_forward_cuda.cu -o roi_align_forward_cuda.cuda.o /data/repos/detectorch/lib/cppcuda/roi_align_forward_cuda.cu:173:82: error: macro "AT_ASSERT" passed 2 arguments, but takes just 1
Same here
https://github.com/CVBox/PyTorchCV/tree/master/extensions/layers I have fixed it! @antocapp
Hello @youansheng, thanks for the reply! What should i do?
I applied the fix from @youansheng
Please try now.
Also, an official Mask RCNN was released by Facebook here https://github.com/facebookresearch/maskrcnn-benchmark
I'm using pytorch 0.4.1, when i ran demo.py,