IndexError: list index out of range

[QueenPuxxi]

Problem description:

When I try to runpython main.py --input_dir input/face --im_path1 90.png --im_path2 15.png --im_path3 117.png --sign realistic --smooth 5, it reports an error:

No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
Traceback (most recent call last):
File "main.py", line 13, in
from models.Embedding import Embedding
File "/root/autodl-tmp/Barbershop/models/Embedding.py", line 3, in
from models.Net import Net
File "/root/autodl-tmp/Barbershop/models/Net.py", line 3, in
from models.stylegan2.model import Generator
File "/root/autodl-tmp/Barbershop/models/stylegan2/model.py", line 11, in
from models.stylegan2.op import FusedLeakyReLU, fused_leaky_relu, upfirdn2d
File "/root/autodl-tmp/Barbershop/models/stylegan2/op/init.py", line 1, in
from .fused_act import FusedLeakyReLU, fused_leaky_relu
File "/root/autodl-tmp/Barbershop/models/stylegan2/op/fused_act.py", line 14, in
os.path.join(module_path, "fused_bias_act_kernel.cu"),
File "/root/miniconda3/envs/Brshop/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1296, in load
keep_intermediates=keep_intermediates)
File "/root/miniconda3/envs/Brshop/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1518, in _jit_compile
is_standalone=is_standalone)
File "/root/miniconda3/envs/Brshop/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1619, in _write_ninja_file_and_build_library
is_standalone=is_standalone)
File "/root/miniconda3/envs/Brshop/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 2014, in _write_ninja_file_to_build_library
cuda_flags = common_cflags + COMMON_NVCC_FLAGS + _get_cuda_arch_flags()
File "/root/miniconda3/envs/Brshop/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1780, in _get_cuda_arch_flags
arch_list[-1] += '+PTX'
IndexError: list index out of range

Can someone help me with that, please?

[MajidShafaee]

Hi. did you find any solution?

[QueenPuxxi]

@MajidShafaee Hello! I give up using this project. In fact, I think that depending on my needs, I can find a hairstyle that suits my needs and give it a face swap. Here's another way of thinking. If you're interested in face swapping, you can try: https://github.com/facefusion/facefusion