[TF-TRT] Avoid padding calculations when not needed #28878
Merged
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
aaroey
approved these changes
May 22, 2019
tensorflow-bot
bot
added
kokoro:force-run
tensorflow-copybara
pushed a commit
that referenced
this pull request
May 22, 2019
…alcs PiperOrigin-RevId: 249437716
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Outdated suggestions cannot be applied.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.
PR #27988 added the following:
setPaddingModeso TRT will automatically calculate padding.setPostPadding/setPostPaddingto perform asymmetric padding without an additionalIPaddingLayer(there was a bug using this for convolutions which was fixed in 5.1.3).For TRT < 5.1.3, we have to compute padding values manually based on the input dimensions. This PR makes it so these calculations are no longer performed for TRT >= 5.1.3 where they are not used.
This PR also simplifies some of the logic determining how to do the padding based on TRT version and adds comments explaining why.