[Frontend, Tensorflow] Support for broadcasting in batch_matmul when shapes differ #8251
+26
−7
Conversation
This file contains hidden or 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
Contributor
Author
mbrookhart
reviewed
Jun 14, 2021
comaniac
reviewed
Jun 15, 2021
mbrookhart
approved these changes
Jun 16, 2021
Contributor
|
Thanks @rohanmukh @comaniac |
Contributor
Author
|
Thanks @comaniac @mbrookhart |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Jun 17, 2021
…shapes differ (apache#8251) * Support for broadcasting in batch_matmul when shapes differ * refactor * refactor logic for reshape in conditional * refactor
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Jun 17, 2021
…shapes differ (apache#8251) * Support for broadcasting in batch_matmul when shapes differ * refactor * refactor logic for reshape in conditional * refactor
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Current implementation of
batch_matmulin TF frontend is not able to handle cases where the shape of the second input differs from the first and a broadcast is needed to complete the operation. Also, in the current logic it always assumed that the shape of second inputshape_yis atleast of length 3. This is not the case is some TF2 models like efficientdet. This PR handles these use cases.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.