augment keypoints in one run #259
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
MhLiao
approved these changes
May 31, 2021
This was referenced Jun 1, 2021
Loovelj
added a commit
to Loovelj/DBNet.pytorch
that referenced
this pull request
Jun 3, 2021
refer MhLiao/DB#259 , luning found this will accelerate the train
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Outdated suggestions cannot be applied.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.
When the number of text boxes is too large (> 500), augmenting poly one by one will incur severe performance degration. According to the performance guide, we can augment all keypoints in the image in one run.
For keypoint-based and heatmap-based augmentation, try to increase the number of items per augmented instance. E.g. augment_keypoints() accepts a list of KeypointsOnImage instances, with each such instance representing the keypoints on an image. Try to place for each image all keypoints in the respective KeypointsOnImage instance instead of splitting them into multiple such instances (which would be more work anyways). The same is true for bounding boxes, heatmaps and segmentation maps.In my case, there are 700 boxes in the image. The processing time is about 3s. After optimization, it becomes 0.03s.