[RELAX][ONNX] Add support for dynamic shape expression in Expand #17504
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
updated slice to convert PrimExpr to PrimValue before sending values to relax.op.strided_slice
removed unnecessary list comprehension
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Outdated suggestions cannot be applied.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.
Expand
Updated Expand converter in onnx frontend to to handle dynamic shape expressions by matching data and target_shape
dimension lengths and converting any target shape elements assigned to -1 to the data shape dimension.
Added regression test to onnx frontend testing Expand with a dynamic shape
Additional small fixes
I replaced int(k.data.numpy()[0]) with int(k.data.numpy().item()) in Trilu since sometimes the data shape is a zero dimensional scalar
I added a function converting from PrimExpr to PrimValue before sending in starts, ends, steps to relax.op.strided_slice since it does not accept PrimeExpr as inputs.