Add size limits to RandomScale transform #462
Merged
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
hadipash
reviewed
Jun 28, 2023
|
@colawyee FCENet's original scaling transformation required size limits. This PR adds this functionality so that you can integrate limits in FCENet if you find it necessary. |
hadipash
reviewed
Jun 30, 2023
hadipash
approved these changes
Jun 30, 2023
Songyuanwei
approved these changes
Jul 4, 2023
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Outdated suggestions cannot be applied.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.
Thank you for your contribution to the MindOCR repo.
Before submitting this PR, please make sure:
Motivation
During training, the RandomScale transform randomly scaled the images in the datasets; however, in some datasets, there are mixtures of small and big images, which, when scaled randomly, may lead to extremely small or extremely large images.
Therefore, this PR implements the logic of taking the minimum and maximum side lengths (
side_limits) as arguments and then using them to calculate the scaling factor, so the randomly scaled images always stay within the specified reasonable limits.Test Plan
(How should this PR be tested? Do you require special setup to run the test or repro the fixed bug?)
Related Issues and PRs
(Is this PR part of a group of changes? Link the other relevant PRs and Issues here. Use https://help.github.com/en/articles/closing-issues-using-keywords for help on GitHub syntax)