YuanxunLu / LiveSpeechPortraits

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
MIT License
1.16k stars 198 forks source link

Explicitly added map_location 👌 #89

Open Kraiwin-Namsri opened 1 year ago

Kraiwin-Namsri commented 1 year ago

I got this error: " If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU. "

https://pytorch.org/docs/stable/generated/torch.load.html

when trying with this command: python demo.py --id May --driving_audio ./data/Input/00083.wav --device cp

Explicitly adding this works: map_location=device

I am not able to try this on CUDA. Please check if this works on CUDA.