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] Enable onnx shape inference in export by default #46629
Conversation
BowenBao
commented
Oct 21, 2020
•
edited
edited
- Enable ONNX shape inference by default.
- ONNX could potentially set inferred shape in output instead of value_infos, checking both to be sure.
- Small fix in symbol_map to avoid overlooking dup symbols.
- Fix scalar_type_analysis to be consistent with PyTorch scalar type promotion logic.
- Correctly handle None dim_param from ONNX inferred shape.
💊 CI failures summary and remediationsAs of commit f7eae4c (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 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 76 times. |
1f490b3
to
b586368
Compare
Codecov Report
@@ Coverage Diff @@
## master #46629 +/- ##
==========================================
+ Coverage 81.25% 81.30% +0.04%
==========================================
Files 1838 1838
Lines 198270 198318 +48
==========================================
+ Hits 161114 161241 +127
+ Misses 37156 37077 -79 |
Hi @BowenBao! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but we do not have a signature on file. In order for us to review and merge your code, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. If you have received this in error or have any questions, please contact us at cla@fb.com. Thanks! |
I'm not clear about this item: Is there any other mechanism to specify shape type other than value_infos? What does it mean to check both? |
Yes, changes in ONNX 1.8 will write inferred shape for outputs of graph to graph outputs. inferred shape for outputs of intermediate node will still be kept in value_infos. |
b5b77cd
to
4a6b5be
Compare
4a6b5be
to
cbc1108
Compare
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.
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.
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.