[ONNX] Update DequantizeLinear21 converter #27351
Merged
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
gkrivor
approved these changes
Oct 31, 2024
gkrivor
changed the title
andrei-kochin
approved these changes
Oct 31, 2024
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Outdated suggestions cannot be applied.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.
Details:
Aligned with the canonical form of the dequantization subgraph.
Reshape op has been moved up right after the Constant, it will be const folded in MOC, this is ok, Reshape const folding doesn't copy a constant, just copies a pointer.
And ConvertLike were replaced with Convert. Perhaps that's a pretty rough change and we need to add a check here that the scale is a contant. And in that case use Convert instead of ConvertLike, if scale is not a constant, maybe we should leave ConvertLike.
Tickets: