[Keras] Fix importing conv2d_transpose for NHWC layout #13998
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
The issue was in the shapes mismatch when `layout=NHWC` was passed to importer. In this case kernel layout in conv2d_transpose operation was set to HWIO but in params HWOI layout was used. And we got the following error: ``` `Tensor[(2, 2, 64, 128), float32]` does not match `Tensor[(2, 2, 128, 64), float32]` ```
Collaborator
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.
Generated by tvm-bot |
echuraev
force-pushed
the
echuraev/fix_keras_conv2d_transpose_nhwc
branch
from
4fa21a5 to
fa81212
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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 issue was in the shapes mismatch when
layout=NHWCwas passed to importer. In this case kernel layout in conv2d_transpose operation was set to HWIO but in params HWOI layout was used. And we got the following error: