8000 what's the meaning of media in input to PerceiverResampler ? Why give time embedding to different media ? Shouldn't given time embedding to different frames? · Issue #301 · mlfoundations/open_flamingo · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
what's the meaning of media in input to PerceiverResampler ? Why give time embedding to different media ? Shouldn't given time embedding to different frames? #301
New issue
New issue
Open
Open
what's the meaning of media in input to PerceiverResampler ? Why give time embedding to different media ? Shouldn't given time embedding to different frames?#301
@Yang-bug-star

Description

@Yang-bug-star
Yang-bug-star
opened on Jun 4, 2024

According to the original paper, the input shape to PerceiverResampler should be (b, T, v, d)，T means the number of frames in video in time and v means the number of visual tokens of one frame. But I'm confused about the concept of media

Metadata

Metadata

Assignees

No one assigned

    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
      0