GFPGAN
GFPGAN copied to clipboard
I cant train the model when set BASICSR_JIT == 'True'
The error is as following: Traceback (most recent call last): File "/data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1723, in _run_ninja_build env=env) File "/data/zx/miniconda3/envs/D22/lib/python3.7/subprocess.py", line 512, in run output=stdout, stderr=stderr) subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1. The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "gfpgan/train.py", line 3, in
RuntimeError: Error building extension 'deform_conv': [1/2] /usr/bin/nvcc -DTORCH_EXTENSION_NAME=deform_conv -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="gcc" -DPYBIND11_STDLIB="libstdcpp" -DPYBIND11_BUILD_ABI="cxxabi1011" -isystem /data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/include -isystem /data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -isystem /data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/include/TH -isystem /data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/include/THC -isystem /data/zx/miniconda3/envs/D22/include/python3.7m -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS_ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 --compiler-options '-fPIC' -std=c++14 -c /data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/basicsr/ops/dcn/src/deform_conv_cuda_kernel.cu -o deform_conv_cuda_kernel.cuda.o
Thanks!
how to resolve it?