Add pytorch's Dataset support and improve augmentation support#8
Merged
Add pytorch's Dataset support and improve augmentation support#8
Conversation
Obi-Wan
force-pushed
the
datasets_and_agumentation
branch
from
2797c35 to
b6ab18c
Compare
Signed-off-by: Nicola VIGANÒ <nicola.vigano@cea.fr>
…or (for reproducibility) Signed-off-by: Nicola VIGANÒ <nicola.vigano@cea.fr>
Signed-off-by: Nicola VIGANÒ <nicola.vigano@cea.fr>
Signed-off-by: Nicola VIGANÒ <nicola.vigano@cea.fr>
Obi-Wan
force-pushed
the
datasets_and_agumentation
branch
from
b6ab18c to
8e135e0
Compare
Contributor
Author
|
This seems to pass all tests. I'm going to merge. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description / Context
Pytorch's
Datasetclass enables creating an abstraction layer for various kinds of datasets, including on-disk and in-memory data. This PR adds support for using derived classes from theDatasetclass in the training of theSupervisedandNoise2Noisealgorithms. Moreover, it adds support forAugmentationclasses. These classes include random flips, random rotations, and the addition of random noise in the form of Gaussian and Poisson noise.For the moment, we focus on the in-memory behavior. We will open a dedicated PR for the on-disk handling of the training/inference data.
TODO
Dataset-derived classesAugmentation-derived classesNotes
This is a much less over-engineered version of the previous implementation of the
Datasetclasses. For the moment, theDataLoaderclass is not used. It might be added in the future if the on-disk usage becomes popular.