Skip to content

C-GQA dataset: Some pairs in train_pairs.txt don't have image examples in the training set #3

Description

@vkhoi

Thank you for the new dataset. I have one question about it. I find 133 pairs in train_pairs.txt that don't have any image examples in the training set. Some examples of them are: "angry person", "long_sleeved shirt", "open drawer", "small duck". Can you check this out?

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions