This repository was archived by the owner on Jul 10, 2021. It is now read-only.
Fix bug when batch_size > dataset size #157
Closed
Conversation
This file contains hidden or 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
If batch size is greater than the total size of the data set, no data will be yielded from _iterate_data. Consequently, no training will happen and you will get a ZeroDivision error for "loss / count" in _batch_impl. Also, it only generates batches of the exact size - any remaining data at the end is not trained on.
|
Happy to merge this, just need one test to catch the problem. See if there's a sensible place to put it with other |
|
If you want me to merge this from your PR, please include the three tests from [7831214]. Thanks again! |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
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Outdated suggestions cannot be applied.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.
If batch size is greater than the total size of the data set, no data will be yielded from _iterate_data. Consequently, no training will happen and you will get a ZeroDivision error for "loss / count" in _batch_impl. Also, it only generates batches of the exact size - any remaining data at the end is not trained on.