Skip to content

Conversation

@jignparm
Copy link
Contributor

@jignparm jignparm commented Jul 10, 2020

Fixes #997.

The input shape into Conv*D operators is sometimes "off by 1", and can be adjusted (broadcasted) to satisfy the spatial rank requirements for the 'add_padding()' function to work correctly and proceed with converting the TF ops.

@jignparm
Copy link
Contributor Author

Fixes #997.

@jignparm jignparm merged commit 38b19b2 into onnx:master Jul 11, 2020
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.

Get ValueError: node *** output needs to be rank 4, is 3 when trying to convert from TF model with Bidirectional ConvLSTM2D Layers

2 participants