Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement RaggedTensorToTensor for tensors with dense (uniform) dims #1676

Merged
merged 2 commits into from
Aug 15, 2021

Conversation

TomWildenhain-Microsoft
Copy link
Contributor

No description provided.

@@ -2460,6 +2460,8 @@ def version_11(cls, ctx, node, **kwargs):
# https://www.tensorflow.org/guide/ragged_tensor#multiple_ragged_dimensions
dense_values = node.input[-1]
nested_splits = node.input[:-1]
err_msg2 = "RaggedTensorToSparse conversion only supports tensors with no dense dimensions"
utils.make_sure(ctx.get_rank(dense_values) in [None, 1], err_msg2)
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

RaggedTensorToSparse was missing this assertion

Signed-off-by: Tom Wildenhain <tomwi@microsoft.com>
@guschmue guschmue merged commit 8c8e585 into master Aug 15, 2021
@guschmue guschmue deleted the tom/fix_ragged_dense_dims branch August 15, 2021 17:02
@TomWildenhain-Microsoft TomWildenhain-Microsoft linked an issue Aug 15, 2021 that may be closed by this pull request
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

ONNX model serving: brodcasting error in Where node.
2 participants