A tutorial to use randomised permutation during training #807
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
for more information, see https://pre-commit.ci
wyli
approved these changes
Jul 19, 2022
|
Thanks @wyli |
boneseva
pushed a commit
to boneseva/MONAI-tutorials
that referenced
this pull request
Apr 21, 2024
…AI#807) * A tutorial to use randomised permutation during training
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Outdated suggestions cannot be applied.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.
Description
While training, if a monai transform chain is defined. It so happens that all the images go through the same transformations. All the transformations are vector quantities, so switching the order of transforms will generate a new augmentation. In the present implementation if you apply any transform more than once, you need to write it multiple times. Instead we are proposing is that the users can specify a dictionary of name of transformation (like rotate, flip or translate etc) and the frequency of transformation (an integer like 1, 2, ). The Augmentation class will then generate random transformation chain on the fly during training. One of the cons of this approach is that the cache method probably cannot be used as the transformations are being generated at random
Status
Ready
Checks