New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Running with --cpu does not work for animation_demo.py #16
Comments
See PR #17 |
Thanks so much for the nice PRs |
You are welcome. I am considering using SAFA for generating some stimuli video for one of my scientific studies, hence my interest in your software. It was not easy to get it working for the modern version of the dependency modules, in particular torch and PyTorch3D. By the way, I could not make SAFA work for the newest version of pytorch (1.12.1) and pytorchvision (0.13.1). The latest PyTorch3D (0.7.1, recently released) works fine with pytorch 1.11.0 and pytorchvision 0.12.0. At any rate, I have created a fork for SAFA. I submitted most of my changes as PRs to the upstream SAFA repository, but not everything. Please take a look at my forked repository and tell me what you think. |
Feel free to make any adaptations for the newest version of PyTorch3D. But please do not use SAFA for any commercial purpose. |
Sure. As I write before, I am looking for a face animation software that can produce controlled audiovisual stimuli for a perception study. No commercial purpose involved, only Science. And your paper in 3DV 2021 will get properly cited, in the case I will use SAFA in my study. |
python animation_demo.py --config config/end2end.yaml --checkpoint ./ckpt/final_3DV.tar --source_image_pth ./assets/EM.jpeg --driving_video_pth ./assets/02.mp4 --relative --adapt_scale --find_best_frame --cpu
gives me:it seems to come from the
animation_demo.py
file with the absence of theif not cpu condition
in line 83.How can I modify the file to solve this properly?
The text was updated successfully, but these errors were encountered: