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
Add drop_last option to data loader in training loop #217
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@PyKEEN-bot test please |
cthoyt
reviewed
Dec 14, 2020
mali-git
reviewed
Dec 14, 2020
mali-git
approved these changes
Dec 14, 2020
@PyKEEN-bot test |
cthoyt
reviewed
Dec 14, 2020
cthoyt
reviewed
Dec 14, 2020
Trigger CI
Trigger CI
Trigger CI
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR supersedes #113.
It adds the
drop_last
option toTrainingLoop.train
. WhenNone
,drop_last=True
if and only if the model contains anyBatchNorm
layers. It can also be provided explicitly to override this default. Moreover, whenbatch_size=1
the training loop will raise an error if the model contains any batch norm layers.