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

Add support for one hot encoding of 0-rank tensor #1771

Conversation

LoicDagnas
Copy link
Contributor

Trying to solve my self this issue #1757 I have been lead to add the support of one hot encoding of 0-rank tensor as it is supported by TensorFlow.

Signed-off-by: Dagnas <dagnas@sinequa.com>
@LoicDagnas LoicDagnas force-pushed the loic-dagnas/feature/add-support-for-zero-rank-one-hot-encoding branch from 38b7fe4 to 982f0cb Compare November 15, 2021 17:28
Signed-off-by: Dagnas <dagnas@sinequa.com>
@guschmue guschmue enabled auto-merge (squash) November 22, 2021 21:25
@guschmue guschmue merged commit 65aaa2c into onnx:master Nov 22, 2021
@LoicDagnas LoicDagnas deleted the loic-dagnas/feature/add-support-for-zero-rank-one-hot-encoding branch November 23, 2021 08:45
@q-ycong-p
Copy link
Contributor

q-ycong-p commented Jan 12, 2022

@LoicDagnas @TomWildenhain-Microsoft @guschmue
This commit caused python setup.py test to throw segmentation fault on the newly added test_onehot_rank0 with onnx==1.7.0. Confirmed that latest onnx==1.10.2 is fine. Can we investigate if it's an easy fix, or only latest onnx is supported?

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.

5 participants