Add unsqueeze and transpose patterns #178
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
slyalin
reviewed
Dec 17, 2024
Comment on lines
+40
to
+55
| SmallVector<ReassociationIndices> expand_groups; | ||
| ReassociationIndices group = ReassociationIndices(); | ||
| SmallVector<int64_t> shape(coords.size() + ov_input_shape.rank().get_length()); | ||
| for (size_t input_idx = 0, coord_idx = 0, i = 0; i < shape.size(); ++i) { | ||
| group.push_back(i); | ||
| if (coord_idx < coords.size() && i == coords[coord_idx]) { | ||
| shape[i] = 1; | ||
| coord_idx++; | ||
| } else { | ||
| const auto& dim = ov_input_shape[input_idx]; | ||
| shape[i] = dim.is_dynamic() ? ShapedType::kDynamic : dim.get_length(); | ||
| input_idx++; | ||
| expand_groups.push_back(group); | ||
| group = ReassociationIndices(); | ||
| } | ||
| } |
There was a problem hiding this comment.
Why cannot we just take it as node->get_output_partial_shape(0)? I believe the shape in MLIR should match the shape from OV.
There was a problem hiding this comment.
Would it be always available? (dynamic shapes?)
There was a problem hiding this comment.
I'd still need to generate the reassociation groups anyway though
There was a problem hiding this comment.
I'd still need to generate the reassociation groups anyway though
There was a problem hiding this comment.
get_output_partial_shape always returns shape, including dynamic shapes, which means a part of the dimensions can be dynamic and you already know how to detect them -- dim.is_dynamic(). But I agree that you still need to build reassociation groups.
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Outdated suggestions cannot be applied.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.
Both rely on the second input to be a constant.
Depends on #177