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.

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

[ONNX Parser] Add warning in case of opset mismatch #8356

Merged
merged 2 commits into from
Jun 29, 2021

Conversation

islavutin
Copy link
Contributor

I faced with the problem that if I incorrectly pass onnx opset parameter to the onnx frontend I am getting the error with some low level error trace without any hint related to incorrect opset. That was difficult to root the reason due to that. That's likely a rare case since most of the time user will not pass opset and rely on converter to detect it. Still it worth to improve the logging to hint user in case of such a situation

Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from Reviewers by @ them in the pull request thread.

Copy link
Contributor

@jwfromm jwfromm left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I like adding this error message, thanks for the change!

@jcf94 jcf94 merged commit 7fddb85 into apache:main Jun 29, 2021
ylc pushed a commit to ylc/tvm that referenced this pull request Sep 29, 2021
* add warning in case of opset mismatch

* fix CI

Co-authored-by: elenaslavutina <elena.slavutina2013@gmail.com>
zxy844288792 pushed a commit to zxy844288792/tvm that referenced this pull request Mar 4, 2022
* add warning in case of opset mismatch

* fix CI

Co-authored-by: elenaslavutina <elena.slavutina2013@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants