This repository has been archived by the owner on Sep 18, 2024. It is now read-only.
More robust random seeding using a numpy generator #352
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Outdated suggestions cannot be applied.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.
Summary
Only initialize the seed once on iterator creation. Maybe an option to reset it could be added.
Update This pull request actually needs more work, because it seems like if you want to synchronize two generators (i.e. images and masks) the geomtric tranformations in the ImageDataGenerator can very easily be non deterministic as well.
Related Issues
#351 - not entirely related to this, but in the same direction of truly reproducable results.
PR Overview