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

LR scheduler only used in eval #1

Open

luciainnocenti opened this issue May 5, 2023 · 1 comment

luciainnocenti commented May 5, 2023 •

edited

Loading

In train.py the LR scheduler is initialized:

    scheduler = ReduceLROnPlateau(optimizer=optimizer, mode='max', patience=1, verbose=True,
                                  factor=params['decay_factor'])

But then it is called on the test set. How is it managed?

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

Author

luciainnocenti commented May 9, 2023

The scheduler is called on the validation test set, which has been split separately from the test set.

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