[Relay][Frontend][ONNX] Allow importing models with malformed Loop nodes. #8475
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mbrookhart
approved these changes
Jul 15, 2021
|
Thanks @jwfromm |
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Sep 29, 2021
…des. (apache#8475) * Snapshot * Undo comments. * Add testing for malformed loop nodes. * Format oops.
zxy844288792
pushed a commit
to zxy844288792/tvm
that referenced
this pull request
Mar 4, 2022
…des. (apache#8475) * Snapshot * Undo comments. * Add testing for malformed loop nodes. * Format oops.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A user recently noted that there are some issues importing some DLRM models generated by Pytorch in this thread. After investigating, I found that the problem is that Pytorch is generating loop nodes without proper output shape information, which causes us to use improper variable shapes. To fix this, we can instead do type inference on the loop body to figure out output shapes on our own. This should be more robust in general.
I've added a test case with a malformed loop node to confirm this fix works. I also removed an old warning that has since been fixed.