search

fudan-generative-vision / hallo

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
https://fudan-generative-vision.github.io/hallo/
MIT License
9.24k stars 1.27k forks source link

How to change the parameters in the py file to train gpu? #157

Open xiaoyu-maka opened 2 months ago

xiaoyu-maka commented 2 months ago

I changed two cpu parameters in inference.py to gpu but still didn't call gpu. Which code parameter should I change to complete gpu training?

xumingw commented 2 months ago

I'm sorry I don't understand your question. Could you provide more details?

xiaoyu-maka commented 2 months ago

I want to use GPU to train this model, but now it's CPU training. What specific location in the code should I change to use my GPU for training

xumingw commented 2 months ago

Please read training part of README