Some Changes to Pascal Loader #255
Open
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
The current version has deprecated functions such as scipy.misc.imsave, and the resizing part generates unwanted values in the label masks. This triggers cuda to stop the training process due to dataloader issues. Edits include: - changing misc functions to cv2.imwrite and cv2.imread - use of nearest neighbor resize method for preserving label integers - adding test set functionality (which could be similar to val set or contain different images) - using aug_with_sbd flag to make augmentation with SBD optional - added test set functionalities (a separate test.txt file should be made in the directory) - some other minor changes Most important reason for proposal: It works!!!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 version has deprecated functions such as scipy.misc.imsave, and the resizing part generates unwanted values in the label masks. This triggers cuda to stop the training process due to dataloader issues.
Edits include:
Most important reason for proposal: It works!!!