Repository navigation
Add TensorRT binding size dimension specification - #36435
Merged
Merged
Conversation
This was referenced Feb 3, 2020
gbaned
requested review from
bixia1 and
sanjoy
and removed request for
sanjoy
February 4, 2020 05:08
bixia1
reviewed
Feb 7, 2020
bixia1
left a comment
bixia1
left a comment
Contributor
There was a problem hiding this comment.
Can you make the PR description more concise and remove the mentioning of the other two PRs?
Contributor
Author
|
Updated the PR description. |
bixia1
approved these changes
Feb 7, 2020
tensorflow-bot
Bot
added
kokoro:force-run
ArmageddonKnight
pushed a commit
to UofT-EcoSystem/tensorflow
that referenced
this pull request
Feb 10, 2020
PiperOrigin-RevId: 294152453 Change-Id: I07ea169bde488ff868f3b5521c8bba58a867658d
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR enables binding size specification (explained below). This is a building block towards enabling inference with dynamic shapes.
Currently dynamic shapes are not used, therefore this PR does not change any existing behavior.
TensorRT bindings are an array of pointers to the input and output buffers for the network. In earlier versions of TensorRT, the size of the input and output tensors had to be specified during engine creation time. Since TensorRT 6, the inputs and outputs can have dynamic shapes (unknown during engine creation time). To perform inference with dynamic shapes, we have to specify the actual dimensions before we run the inference. This is implemented in this PR.