-
-
Notifications
You must be signed in to change notification settings - Fork 85
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.
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
GPU enabled model raises Exception: expected self and mask to be on the same device, but got mask on cpu and self on cuda:0 #3
Comments
Hi there, |
Hi Maciej, Thank you very much for your feedback! Actually, I noticed this bug and fixed it in this commit to branch And in your PR, you create an additional argument |
Thanks for looking into it. I see there is a new build available in PyPI. Thank you for the tips on my code. |
Absolutely my pleasure! 😃 Yes, I released PyPOTS v0.0.7 on PyPI to fix this bug together with some other issues. And many thanks to your PR, which is the first one to PyPOTS and means a lot to me, though it isn't merged into the main branch. I sincerely invite you to join the community and contribute to PyPOTS together. If you have ideas or comments on PyPOTS, please let me know, and your PRs are always welcome! |
Hello,
great library, but using gpu enabled machine results in errors.
pypots version = 0.0.6 (the one available in PyPI)
code to replicate problem:
results:
i suspect that you call
.to(device)
too early on data. You might also overridedevice
parameter when initiating new tensors (i.e. in torch.ones in parse_delta)Best regards!
The text was updated successfully, but these errors were encountered: