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

Update TensorRT parser to fix accuracy issue in some opset11 models #5442

Merged
merged 1 commit into from
Oct 10, 2020
Merged

Update TensorRT parser to fix accuracy issue in some opset11 models #5442

merged 1 commit into from
Oct 10, 2020

Conversation

stevenlix
Copy link
Contributor

  1. Update Onnx-TensorRT parser to include latest fix
    The fix solved the issue of accuracy loss in some opset11 models, such as yolov4 in onnx model zoo.
    The reason is certain new attributes of opset11 Resize operator are not supported in TensorRT7.1 and also are not handled properly in the parser.
  2. Move cudaDeviceSynchronize right after enquenV2 to make sure TRT outputs are synced before fetching

@stevenlix stevenlix requested a review from a team as a code owner October 9, 2020 22:30
@stevenlix stevenlix mentioned this pull request Oct 9, 2020
Closed
@stevenlix stevenlix merged commit 186f066 into master Oct 10, 2020
@stevenlix stevenlix deleted the stevenlix/accuracy branch October 10, 2020 04:49
tianleiwu pushed a commit that referenced this pull request Oct 10, 2020
@stevenlix @tianleiwu
update onnx-tensorrt submodule (#5442)
2df3657
tianleiwu pushed a commit that referenced this pull request Oct 12, 2020
@stevenlix @tianleiwu
update onnx-tensorrt submodule (#5442)
bcbcb25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jywu-msft jywu-msft jywu-msft approved these changes

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
@stevenlix @jywu-msft