Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[v1.4.x] [MXNET-703] Update to TensorRT 5, ONNX IR 3. Fix inference bugs. #13897

Merged
merged 3 commits into from
Jan 17, 2019

Conversation

KellenSunderland
Copy link
Contributor

@KellenSunderland KellenSunderland commented Jan 16, 2019

Description

This PR updates the IR which is passed to TensorRT to use version3 of the spec, which aligns much better with MXNet defaults and results in a decrease in boilerplate code. This update also fixes some bugs when building inference engines that were resulting in feature vectors that were very different from what they should have been.

Fixes #12598
Fixes #13113

Master PR with review history: #13310

Checklist

Essentials

Please feel free to remove inapplicable items for your PR.

  • The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant JIRA issue created (except PRs with tiny changes)
  • Changes are complete (i.e. I finished coding on this PR)
  • All changes have test coverage:
  • Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
  • Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
  • Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
  • Code is well-documented:
  • For user-facing API changes, API doc string has been updated.
  • For new C++ functions in header files, their functionalities and arguments are documented.
  • For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
  • Check the API doc at http://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
  • To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

Marco:
Resolves #13459

This works around a CUDA 10 cmake issue documented here:
clab/dynet#1457

This fix is temporary; once an updated cmake package is published to Ubuntu's
package repo it may be reverted.
@KellenSunderland KellenSunderland changed the title [MXNET-703] Update to TensorRT 5, ONNX IR 3. Fix inference bugs. [v1.4.x] [MXNET-703] Update to TensorRT 5, ONNX IR 3. Fix inference bugs. Jan 16, 2019
@stu1130
Copy link
Contributor

stu1130 commented Jan 16, 2019

@mxnet-label-bot add [pr-awaiting-review]
Thanks for the great work @KellenSunderland

@marcoabreu marcoabreu added the pr-awaiting-review PR is waiting for code review label Jan 16, 2019
@KellenSunderland
Copy link
Contributor Author

@marcoabreu Would you be able to review this PR? It's the same as the other PR, but it makes a small change to the legacy Jenkinsfile to account for cmake builds.

@marcoabreu marcoabreu merged commit 9edf53a into apache:v1.4.x Jan 17, 2019
lanking520 pushed a commit to lanking520/incubator-mxnet that referenced this pull request Feb 18, 2019
…ugs. (apache#13897)

* [MXNET-703] Install CUDA 10 compatible cmake

This works around a CUDA 10 cmake issue documented here:
clab/dynet#1457

This fix is temporary; once an updated cmake package is published to Ubuntu's
package repo it may be reverted.

* [MXNET-703] Update to TensorRT 5 ONNX IR 3. Fix inference bugs.

* [MXNET-703] Describe onnx opsets and major version
lanking520 pushed a commit to lanking520/incubator-mxnet that referenced this pull request Apr 26, 2019
…ugs. (apache#13897)

* [MXNET-703] Install CUDA 10 compatible cmake

This works around a CUDA 10 cmake issue documented here:
clab/dynet#1457

This fix is temporary; once an updated cmake package is published to Ubuntu's
package repo it may be reverted.

* [MXNET-703] Update to TensorRT 5 ONNX IR 3. Fix inference bugs.

* [MXNET-703] Describe onnx opsets and major version
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
pr-awaiting-review PR is waiting for code review
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants