Try to propagate input data layout to outputs for FINN ops#229
Merged
jmitrevs merged 1 commit intofastmachinelearning:mainfrom Jan 29, 2026
Merged
Try to propagate input data layout to outputs for FINN ops#229jmitrevs merged 1 commit intofastmachinelearning:mainfrom
jmitrevs merged 1 commit intofastmachinelearning:mainfrom
Conversation
makoeppel
requested changes
Jan 23, 2026
Collaborator
makoeppel
left a comment
makoeppel
left a comment
There was a problem hiding this comment.
Can you tell us a bit what this PR does?
makoeppel
approved these changes
Jan 23, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Without layout annotations, FINN tries to guess purely based on the rank (number of dimensions) of a tensor, or even uses some hard-coded defaults, which is error-prone. We can do better by at least trying to propagate layout annotations from input to output, even if this won't be the final solution. @fpjentzsch could maybe comment on which models in our FINN+ flow were affected by this. @auphelia should maybe have a look as well as this is rather fundamental to FINN.