When I run scripts in python test.py --name=face_recon_feat0.2_augment --epoch=20 --img_folder=./datasets/examples,there is always an error: No module named 'nvdiffrast_plugin_gl'
loading the model from ./checkpoints/face_recon_feat0.2_augment/epoch_20.pth
0 ./datasets/examples/000002.jpg
Traceback (most recent call last):
File "test.py", line 72, in
main(0, opt,opt.img_folder)
File "test.py", line 62, in main
model.test() # run inference
File "/home/jlsl/Desktop/share/leyu/Deep3DFaceRecon_pytorch/models/base_model.py", line 162, in test
self.forward()
File "/home/jlsl/Desktop/share/leyu/Deep3DFaceRecon_pytorch/models/facerecon_model.py", line 139, in forward
self.pred_vertex, self.facemodel.face_buf, feat=self.pred_color)
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/jlsl/Desktop/share/leyu/Deep3DFaceRecon_pytorch/util/nvdiffrast.py", line 58, in forward
self.glctx = dr.RasterizeGLContext(device=device)
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/nvdiffrast/torch/ops.py", line 221, in init
self.cpp_wrapper = _get_plugin(gl=True).RasterizeGLStateWrapper(output_db, mode == 'automatic', cuda_device_idx)
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/nvdiffrast/torch/ops.py", line 118, in _get_plugin
torch.utils.cpp_extension.load(name=plugin_name, sources=source_paths, extra_cflags=opts, extra_cuda_cflags=opts+['-lineinfo'], extra_ldflags=ldflags, with_cuda=True, verbose=False)
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 974, in load
keep_intermediates=keep_intermediates)
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1190, in _jit_compile
return _import_module_from_library(name, build_directory, is_python_module)
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1534, in _import_module_from_library
file, path, description = imp.find_module(module_name, [path])
File "/home/jlsl/Desktop/share/anaconda3/envs/deep3d_pytorch/lib/python3.6/imp.py", line 297, in find_module
raise ImportError(_ERR_MSG.format(name), name=name)
ImportError: No module named 'nvdiffrast_plugin_gl'
Have you solved this problem?
If you are using Windows, you'd probably faced this issue, I had initially and I moved the implenetation to Google Colab, and everything went fine from there
@AhmedMedani01 can you please state how you implemented it in colab? I am having trouble setting it up