Skip to content

Feature brainstorming #4

Open
Open
@dmarx

Description

  • loss scoring
  • multi-perceptor
  • weighted multi-perceptor
  • cutout methods? + augs? make that an independent library maybe?
  • perceptor weight interpolations/schedules - https://discord.com/channels/729741769192767510/730484623028519072/956979309686423602
  • API should be agnostic wrt media type, i.e. contrasting modalities could both be text, or one be audio and other video, etc.
  • optionally augment w positional information/embeddings?
  • Maybe some minimal translation API to facilitate use by non-english users and conversely support for non-english models
  • Check for installed/available CLIP, use vendored if not available

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions