Remove and Replace Unnecessary Augmentations #461
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
hadipash
requested review from
SamitHuang,
liangxhao,
Songyuanwei and
VictorHe-1
hadipash
approved these changes
Jun 28, 2023
SamitHuang
approved these changes
Jun 29, 2023
liangxhao
approved these changes
Jun 29, 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Outdated suggestions cannot be applied.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
Two unnecessary transformation classes existed in the code for detection transforms i.e. GridResize and ScalePadImage, which were essentially special implementations of the parent transform DetResize. This PR removes the two child transforms and replaces them with the more concise DetResize implementation.
Also, all instances of GridResize and ScalePadImage in several configuration files are also removed and replaced accordingly. The changes were checked by evaluating the models on the datasets with updated config files - the metrics remained the same.
Moreover, it was realized during the checking that the evaluation metrics for DBNet MobileNetv3 on the ICDAR2015 dataset were incorrectly documented with low percentages. Thus, they are also corrected in this PR.
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)