"RuntimeError: Tensors must be CUDA and dense" when i run train_vae_sevirlr.py for train
Open
bug
- Dominant language
- Python
- Stars
- 159
- Forks
- 10
- PR merge metrics
- No merged PRs in 30d
Description
It seems that there is an error when using torchmetrics to calculate the loss indicator. When I loaded the pre-trained model weights for testing, and subsequent training prediff or test prediff, no such error was reported. I was wondering if anyone has encountered this problem? I hope you can take the time to answer my questions
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.