Add onnx export function for pix2struct model #1815
Merged
Conversation
This file contains 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 docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
fxmarty
approved these changes
Apr 15, 2024
young-developer
pushed a commit
to young-developer/optimum
that referenced
this pull request
May 10, 2024
Add onnx export for pix2struct
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR adds an export option to pix2struct model (document vision-language model) by optimizing its ViT encoder
Before submitting
I have tested the export locally and have seen the model outputs the same captions as the original model (exported https://huggingface.co/google/pix2struct-screen2words-base and tested on https://github.com/google-research-datasets/screen2words dataset)
If there is more testing that I need to do or document the change somewhere please let me know
Who can review?
@fxmarty, @echarlaix, @JingyaHuang, @michaelbenayoun