search

zyainfal / One-Shot-Face-Swapping-on-Megapixels

One Shot Face Swapping on Megapixels.
Other
314 stars 40 forks source link

ImportError: No module named 'fused'? #34

Open postcw opened 2 years ago

postcw commented 2 years ago

Traceback (most recent call last): File "inference.py", line 4, in from megafs import resnet50, HieRFE, Generator, FaceTransferModule File "/root/data/deepfake_Generate_Comparative_Experiment/One-Shot-Face-Swapping-on-Megapixels-main/inference/megafs.py", line 11, in from op import FusedLeakyReLU, fused_leaky_relu, upfirdn2d File "/root/data/deepfake_Generate_Comparative_Experiment/One-Shot-Face-Swapping-on-Megapixels-main/inference/op/init.py", line 1, in from .fused_act import FusedLeakyReLU, fused_leaky_relu File "/root/data/deepfake_Generate_Comparative_Experiment/One-Shot-Face-Swapping-on-Megapixels-main/inference/op/fused_act.py", line 16, in os.path.join(module_path, "fused_bias_act_kernel.cu"), File "/opt/conda/envs/Mega/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 661, in load is_python_module) File "/opt/conda/envs/Mega/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 841, in _jit_compile return _import_module_from_library(name, build_directory, is_python_module) File "/opt/conda/envs/Mega/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1048, in _import_module_from_library file, path, description = imp.find_module(module_name, [path]) File "/opt/conda/envs/Mega/lib/python3.6/imp.py", line 297, in find_module raise ImportError(_ERR_MSG.format(name), name=name) ImportError: No module named 'fused'

zyainfal commented 2 years ago

see issue #32

postcw commented 2 years ago

Sorry, I looked at question #32 and I still couldn't find how to fix this. Question 32 is for windows, I am running on linux, don't know if you have encountered this before?

zyainfal commented 2 years ago

I didn't encounter this problem before, but https://animadversio.github.io/tech_note/debugging-stylegan2 does give a Linux solution, you may want to check it.