issues
search
guoqincode
/
Open-AnimateAnyone
Unofficial Implementation of Animate Anyone
2.9k
stars
233
forks
source link
About multi-GPU training
#31
Closed
vesdas
closed
9 months ago
vesdas
commented
9 months ago
Thank you for your contributions! There are two questions below:
I have observed that the training duration using two RTX 6000 ada GPUs exceeds the time it takes with a single GPU. Is this an expected phenomenon?
I encountered the phenomenon of gradient explosion during the training process.
guoqincode
commented
9 months ago
To improve GPU utilization, you can change the Dataset to lmdb format or increase the resolution to 512,768.
I have not encountered this phenomenon, you can try to use the latest training code, it will still appear, suggested to reduce the learning rate.
Thank you for your contributions! There are two questions below: