OpenTalker/video-retalking

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

zachysaur opened this issue · 6 comments

zachysaur commented

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

ashwani-ver commented

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

Go to file /usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py and change line number 8 to:

from torchvision.transforms.functional import rgb_to_grayscale
Got the solution from AUTOMATIC1111/stable-diffusion-webui#13985

  • 👍2
ashwani-ver commented

also use python version 3.10.12 for creating environment instead of 3.8. For me it worked.

zachysaur commented

i fixed it

only-ns commented 
conda create -n video_retalking python=3.10 -y
conda activate video_retalking
conda install ffmpeg -y
conda install cmake==3.25.2 -y
pip3 uninstall torch torchvision torchaudio -y
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install -r requirements.txt
sachin7695 commented

i fixed it

can you tell me what exactly you did to fix this?