Optimize BatchNormalization by avoiding tensor slicing #661
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
Since the tensor is contiguous and we only need the data for each chunk, we can replace N * C `slice_mut` calls with a much cheaper `chunks_mut` iterator. This made BatchNormalization ~10% faster on a MobileNet v4 model where there are layers with many channels but a relatively small number of elements per channel.
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Outdated suggestions cannot be applied.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.
Since the tensor is contiguous and we only need the data for each chunk, we can replace N * C
slice_mutcalls with a much cheaperchunks_mutiterator.This made BatchNormalization ~10% faster on a MobileNet v4 model where there are layers with many channels but a relatively small number of elements per channel.