Changed the shuffle method #12
Open
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
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Outdated suggestions cannot be applied.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.
The current method for creating x_neg shuffles the indices for labels and re-distributes them. However, this method lefts roughly 10% of labels unchanged, and hence 10% of x_neg pics are actually the 'good' samples.
I attempted to solve this problem by introducing a mask layer that contains random ints from 1 to 9, adding it to the original y data, and finding the remainder of 10. This ensures that the new distribution is i.i.d (as randint is i.i.d) and no more unchanged values after the shuffle.