Skip to content

New problems: Weighted Cross entropy loss, Focal Loss #558

Description

@komaksym

There are 3 levels of solutions to multiclass classification with imbalanced datasets:

  1. data
  2. algorithm
  3. eval

Weighted Cross entropy loss and Focal Loss are often used on algorithm level. Can work on these too, eventually, if needed

Activity

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

Metadata

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