Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Probable FLAVA multimodal encoder bug #530

Open
rishabhm12 opened this issue Oct 14, 2024 · 1 comment
Open

Probable FLAVA multimodal encoder bug #530

rishabhm12 opened this issue Oct 14, 2024 · 1 comment

Comments

@rishabhm12
Copy link

🚀 The feature, motivation and pitch

In flava multimodal encoder, why don't we pass an attention mask to mask out '[PAD]' embeddings coming from text encoder? Is this a bug or intentional?

multimodal/torchmultimodal/models/flava/model.py

Line 197 in e4d288b

multimodal_outputs = self.encode_mm(

Alternatives

No response

Additional context

No response
@rishabhm12
Copy link
Author

@ebsmothers

@rishabhm12 rishabhm12 changed the title FLAVA multimodal encoder bug Probable FLAVA multimodal encoder bug Oct 15, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@rishabhm12