This repository was archived by the owner on Aug 15, 2019. It is now read-only.
Disable packed depthwiseConv. #1796
Merged
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
dsmilkov
approved these changes
Jun 19, 2019
There was a problem hiding this comment.
Reviewed 2 of 2 files at r1.
Reviewable status:complete! 1 of 1 approvals obtained (waiting on @dsmilkov and @nsthorat)
This was referenced Jul 2, 2019
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
This fixes tensorflow/tfjs#1673
It turns out our current version of packed depthwise conv is only optimal for certain ratios of input size / input depth / filter size.
I think it makes sense to disable for now while I figure out how to make a more generally optimal kernel: tensorflow/tfjs#1679
Current version also has accuracy issue: tensorflow/tfjs#1652
To see the logs from the Cloud Build CI, please join either
our discussion
or announcement mailing list.
This change is