Handle image_embeds in ViltModel #16696
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 documentation is not available anymore as the PR was closed or merged. |
ydshieh
requested review from
NielsRogge,
FrancescoSaverioZuppichini and
sgugger
sgugger
approved these changes
Apr 11, 2022
There was a problem hiding this comment.
LGTM, but let's wait for @NielsRogge final review before merging!
NielsRogge
reviewed
Apr 11, 2022
Comment on lines
819
to
821
| image_batch_size = pixel_values.shape[0] if pixel_values is not None else image_embeds.shape[0] | ||
| if image_batch_size != batch_size: | ||
| raise ValueError("The text inputs and image inputs need to have the same batch size") |
There was a problem hiding this comment.
Maybe for consistency, we can call the other one text_batch_size (instead of batch_size).
There was a problem hiding this comment.
done :-) & wait for green CI
NielsRogge
approved these changes
Apr 11, 2022
Not for this PR. I tried to fix a CI (vit-mae), which was about |
elusenji
pushed a commit
to elusenji/transformers
that referenced
this pull request
Jun 12, 2022
* update * batch_size -> text_batch_size Co-authored-by: ydshieh <[email protected]>
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Outdated suggestions cannot be applied.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?
Handle
image_embedsinViltModel/ViltForImagesAndTextClassification.(looks like
Viltis the first model introducingimage_embedsargument.)More Info
The
image_embedsinViltForImagesAndTextClassificationshould havenum_imagesdimension aspixel_valueshas, as far as I understand.