Adding batch-size to dataset_splitter #120
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
willgraf
requested changes
Oct 5, 2020
| splits = [0.001, 0.3, 1] | ||
| ds = DatasetSplitter(splits=splits, seed=0) | ||
| split_dict = ds.split(train_dict=data_dict) | ||
| print(split_dict['0.001']['X']) |
There was a problem hiding this comment.
Remove the print statement.
Suggested change
| print(split_dict['0.001']['X']) |
willgraf
approved these changes
Oct 5, 2020
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Outdated suggestions cannot be applied.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.
The current dataset splitter will return exactly the number of images corresponding to each split ratio provided. However, to maintain a constant batch size during training, for splits that are smaller than the batch size, we want to duplicate the images in that split, up to the batch size.
This PR adds the option to specify a min_size parameter for all splits. If any split results in fewer than that many images, the images are duplicated up to the min size.