Open wedgeewoo opened 1 year ago
pip install scikit-image
Do i install this in the /modules or in the main directory
It doesn't matter, pip install
or conda install
is global
now im getting this
File "A:\Thin-Plate-Spline-Motion-Model\logger.py", line 7, in
Maybe we are using different versions, you can try this
pip install -U scikit-image==0.18.3
AssertionError: Torch not compiled with CUDA enabled
BTW im using Python 3.10 and not 3.9. would this cause an issue?
you installed the cpu version of torch, you can follow the instructions on pytorch.org to install the appropriate version of torch
or you can run the code with cpu mode
python demo.py --config config/vox-256.yaml --checkpoint checkpoints/vox.pth.tar --source_image assets/source.png --driving_video assets/driving.mp4 --mode relative --find_best_frame --result_video SD_Avatar_Video.mp4 --cpu
i did cpu mode after trying to get gpu to work. I was able to get the cpu mode working after installing face alignment (pip install face-alignment==1.1.1), used your commands and i was able to render a video! Thanks for the help
Im missing something about the gpu version of pytorch, im sure i followed the instructions correctly but I'm still unable to use the GPU. Still though thanks for the awesome repo
A:\Thin-Plate-Spline-Motion-Model>set CUDA_VISIBLE_DEVICES=0 & python run.py --config config/vox-256.yaml --checkpoint checkpoints/vox.pth.tar --source_image assets/source.png --driving_video assets/driving.mp4 --find_best_frame --result_video SD_Avatar_Video.mp4 Traceback (most recent call last): File "A:\Thin-Plate-Spline-Motion-Model\run.py", line 9, in
from frames_dataset import FramesDataset
File "A:\Thin-Plate-Spline-Motion-Model\frames_dataset.py", line 2, in
from skimage import io, img_as_float32
ModuleNotFoundError: No module named 'skimage'
How do i fix this? is this a dependency that can be added in the requirements.txt or is this something more complicated?