DCNv2
DCNv2 copied to clipboard
Deformable Convolutional Networks v2 with Pytorch
python -c "import torch; print(torch.version)" 1.10.2 DCNv2$ ./make.sh running build running build_ext /home/azuryl/anaconda3/envs/visdet3d/lib/python3.6/site-packages/torch/utils/cpp_extension.py:381: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back...
There are many libraries deprecated that are used here and cant be used with pytorch 1.11 and higher (as TH/TH.h). The repository "https://github.com/lbin/DCNv2/tree/pytorch_1.11" has been updated with these updates for...
Hello, I've tried to build DCNv2 on Ubuntu with python 3.8 in venv. `sudo ~/work/projects/pricetag-ocr/venv/bin/python setup.py build develop` So I have error: `In file included from /home/tis/work/projects/pricetag-ocr/venv/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:11, from /home/tis/work/projects/pricetag-ocr/venv/lib/python3.8/site-packages/torch/include/ATen/Context.h:4, from...
Hi! How to solve this problem?
torch 1.7.1 cuda 11.0 cudnn 8.1 python 3.7 python setup.py build develop warnings.warn('Error checking compiler version for {}: {}'.format(compiler, error)) building '_ext' extension
When I successful sh 'make.sh', I got this import error , is there anyone who have met the same problem before?
Hi everyone, after i run ./make.sh i got the next error: fatal error: ATen/cuda/CUDAContext.h: No such file or directory 5 | #include | ^~~~~~~~~~~~~~~~~~~~~~~~~ compilation terminated. error: command '/usr/bin/nvcc' failed...
I have the issue when trying to run testcpu.py or testcuda.py this is the error message \FairMOT\DCNv2> python testcpu.py Traceback (most recent call last): File "testcpu.py", line 11, in from...