keras-team/keras

Feature request: Add SparseCategoricalFocalCrossentropy

Open

#23,442 opened on Aug 15, 2026

View on GitHubContributor guide
 (3 comments) (0 reactions) (2 assignees)Python (19,760 forks)batch import
Good first issuepr-approved

Repository metrics

Stars
 (64,249 stars)
PR merge metrics
 (PR metrics pending)

Description

Summary

Add sparse-label support for categorical focal crossentropy through:

  • keras.losses.sparse_categorical_focal_crossentropy
  • keras.losses.SparseCategoricalFocalCrossentropy

Keras currently provides CategoricalFocalCrossentropy, which expects one-hot labels, and SparseCategoricalCrossentropy, which accepts integer labels. There is no corresponding focal loss for sparse categorical labels.

Motivation

Sparse labels are common in semantic segmentation, token classification, and multiclass problems with many classes. Converting these labels to one-hot tensors solely to use focal loss increases memory usage and adds unnecessary preprocessing.

A native sparse implementation would provide focal loss while preserving integer labels and Keras' backend-agnostic behavior.

Proposed API

keras.losses.SparseCategoricalFocalCrossentropy(
    alpha=0.25,
    gamma=2.0,
    from_logits=False,
    ignore_class=None,
    axis=-1,
    reduction="sum_over_batch_size",
    name="sparse_categorical_focal_crossentropy",
    dtype=None,
)

I would like to work on this if the contribution makes sense.

Contributor guide

Research direction
Investigate the existing implementations of CategoricalFocalCrossentropy and SparseCategoricalCrossentropy in Keras, understand how sparse labels are processed, and explore the Keras ops to implement a backend agnostic version. Also review issue comments and any linked PRs for context on expected changes.
Tech stack
python
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60