Skip to content
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.

Sign up for GitHub

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

Jump to bottom

这个是显存不够吗？ #32

Open
Chromer163 opened this issue Apr 7, 2023 · 3 comments
Open

这个是显存不够吗？ #32

Chromer163 opened this issue Apr 7, 2023 · 3 comments

Comments

@Chromer163
Copy link

Traceback (most recent call last):
File "svc_trainer.py", line 46, in
train(0, args, args.checkpoint_path, hp, hp_str)
File "/home/yango/code/Thin-Plate-Spline-Motion-Model/third_party/DINet/third_party/lora-svc/utils/train.py", line 109, in train
validate(hp, args, model_g, model_d, valloader, stft, writer, step, device)
File "/home/yango/code/Thin-Plate-Spline-Motion-Model/third_party/DINet/third_party/lora-svc/utils/validation.py", line 22, in validate
mel_fake = stft.mel_spectrogram(fake_audio.squeeze(1))
File "/home/yango/code/Thin-Plate-Spline-Motion-Model/third_party/DINet/third_party/lora-svc/utils/stft.py", line 90, in mel_spectrogram
center=self.center, pad_mode='reflect', normalized=False, onesided=True, return_complex=False)
File "/home/yango/.conda/envs/dinet/lib/python3.7/site-packages/torch/functional.py", line 607, in stft
normalized, onesided, return_complex)
RuntimeError: cuFFT error: CUFFT_INTERNAL_ERROR
@MaxMax2016
Copy link
Collaborator

torch是什么版本呢？

@Chromer163
Copy link
Author

4090显卡，torch.version==1.12.0

@MaxMax2016
Copy link
Collaborator

我用3060 6G的笔记本跑的微调，应该不是显存不够；

应该是这个问题：pytorch/pytorch#88038

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@MaxMax2016 @Chromer163