MatrixDiagPartV3: Change consts to dynamic ops #948
Merged
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
tf2onnx/onnx_opset/tensor.py
Outdated
| xstart_2 = ctx.make_node('Cast', [xstart_1.output[0]], attr={'to': TensorProto.INT64}) | ||
| xstart_3 = ctx.make_node('Add', [xstart_2.output[0], const_neg_one]) | ||
| xstart_4 = ctx.make_node('Range', [k1_scalar.output[0], xstart_3.output[0], const_neg_one]) | ||
| xstart_4 = ctx.make_node('Range', [k1_scalar, xstart_3.output[0], const_neg_one]) |
Collaborator
There was a problem hiding this comment.
Is const_neg_one a scalar?
Contributor
Author
There was a problem hiding this comment.
It's not a scalar, but it seems to work successfully with Range() function in opset 11 (i.e. unit tests pass).
Collaborator
There was a problem hiding this comment.
What if I am with opset 12 then?
Contributor
Author
There was a problem hiding this comment.
Both opset 11 and 12 are passing unit tests (see checks).
RandySheriffH
approved these changes
Jun 3, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
The input data shape may contain -1 in one of the dimensions, so the shape is not always known before hand.
This PR handles the scenario of a -1 in the shape, which is required by MatrixDiagSetV3