[nGraph] MatMul - Remove fused op and align output shape inference #2866
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
mitruska
changed the title
slyalin
reviewed
Oct 29, 2020
slyalin
reviewed
Oct 29, 2020
slyalin
reviewed
Oct 29, 2020
slyalin
requested changes
Oct 29, 2020
mitruska
commented
Oct 29, 2020
Merged
slyalin
requested changes
Nov 3, 2020
|
@ilyachur You're right, done. |
mbencer
approved these changes
Nov 9, 2020
ilyachur
reviewed
Nov 9, 2020
postrational
approved these changes
Nov 9, 2020
ilyachur
approved these changes
Nov 10, 2020
slyalin
requested changes
Nov 10, 2020
slyalin
requested changes
Nov 11, 2020
slyalin
requested changes
Nov 11, 2020
slyalin
approved these changes
Nov 12, 2020
mryzhov
pushed a commit
to mryzhov/openvino
that referenced
this pull request
Dec 16, 2020
…penvinotoolkit#2866) To follow MatMul spec update for 1D tensors this PR removes FusedOp decomposition for MatMul without changing current MatMul output shape inference logic (numpy/onnx aligned). Based on previous PR openvinotoolkit#2212 that follows rather current spec logic.
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Outdated suggestions cannot be applied.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.
To follow MatMul spec update for 1D tensors this PR introduces FusedOp and decompose removal without changing current MatMul output shape inference logic (numpy/onnx aligned).
Based on previous PR #2212 that follows rather current spec logic.