Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Perception: turn back to TensorRT for pfe inference #12974

Merged
merged 1 commit into from
Nov 13, 2020
Merged

Perception: turn back to TensorRT for pfe inference #12974

merged 1 commit into from
Nov 13, 2020

Conversation

jeroldchen
Copy link
Contributor

  1. Turn back to TensorRT from libtorch, because pfe libtorch inference has some stability problems.
  2. Optimize pfe onnx-tensorrt inference time which is even slightly shorter than using libtorch.

@unacao unacao self-requested a review November 13, 2020 00:41
@jeroldchen jeroldchen merged commit 295e13e into ApolloAuto:master Nov 13, 2020
@jeroldchen jeroldchen deleted the fix_crash branch November 13, 2020 03:16
@PGLF-EAP PGLF-EAP mentioned this pull request Dec 3, 2020
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@guoweiwan guoweiwan guoweiwan approved these changes

@storypku storypku Awaiting requested review from storypku

@zhoujie3 zhoujie3 Awaiting requested review from zhoujie3

@xiaoMrzhang xiaoMrzhang Awaiting requested review from xiaoMrzhang

@panfengsu panfengsu Awaiting requested review from panfengsu

@unacao unacao Awaiting requested review from unacao

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@jeroldchen @guoweiwan