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] Update squeeze test for opset 9 #45369
Conversation
💊 CI failures summary and remediationsAs of commit bc02b94 (more details on the Dr. CI page):
Extra GitHub checks: 1 failed
codecov.io: 1 failed
This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions on the GitHub issue tracker or post in the (internal) Dr. CI Users group. This comment has been revised 5 times. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There's a related test failure.
How was this test passing before this update?
After looking, i think it's the similar issue of runtime shape inference within if subblock. The change in the test makes input sizes static instead of dynamic, so shape inference is able to check the dim and errors it shouldn't happen as dim != 1, though in reality it won't since it's inside the if block which conditions on dim != 1 However i think for this one I should update the symbolic. Going forward with shape inference we should be safe to consider any static shape being static at runtime as well. Dynamic ones should be inferred as dynamic, or marked as such by using |
310303d
to
6268036
Compare
Codecov Report
@@ Coverage Diff @@
## master #45369 +/- ##
==========================================
- Coverage 68.50% 68.48% -0.02%
==========================================
Files 408 408
Lines 52484 52493 +9
==========================================
- Hits 35952 35951 -1
- Misses 16532 16542 +10
Continue to review full report at Codecov.
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Thanks!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@bzinodev has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
Summary: - rand/randn: the type signature of int[] is different in scripting, thus failing the check. - where: scripting produces dynamic cases which are supported by `unbind` export of higher opsets. - test_list_pass: this test fails when using new scripting api, should be fixed by #45369 Pull Request resolved: #45793 Reviewed By: mrshenli Differential Revision: D24566096 Pulled By: bzinodev fbshipit-source-id: 6fe0925c66dee342106d71c9cbc3c95cabe639f7
Only under static axes does opset 9 supports no-op squeeze when dim is not 1.
Updating the test case where it was setting dynamic axes.