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

Error in backward #14

Open

FiorenzoParascandolo1 opened this issue Dec 17, 2024 · 1 comment

FiorenzoParascandolo1 commented Dec 17, 2024

I got this error during backward:

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [CUDAComplexFloatType [8, 2, 4096, 2]], which is output 0 of ViewAsComplexBackward0, is at version 2; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

I'm using standard hyperparameters

The text was updated successfully, but these errors were encountered:

Collaborator

bhheo commented Dec 18, 2024

Hi

I need information to solve the error
Could you provide more details about your case to reproduce the error?

Which training script did you use, deit or SwinTransformer?
What is the version of PyTorch (torch.__version__)?

If you provide this information, I will try to reproduce the error and debug it

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment