# keras-team/keras-cv

Industry-strength Computer Vision workflows with Keras

Repository: https://github.com/keras-team/keras-cv
Canonical: https://ross.abutalabs.com/products/keras-cv
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2026-03-05T23:54:07+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 70, release rhythm 8, longevity 100
- inputs: {"age_days": 2298, "days_push": 181, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1055, forks 324 (observed 2026-08-28T04:03:24.245309+00:00)

## What it is
KerasCV is a library of modular computer vision components built on Keras 3 that work natively with TensorFlow, JAX, or PyTorch. It provides pretrained models, layers, metrics, and augmentation tools for tasks like classification, object detection, segmentation, and image generation. Development has moved to KerasHub, so this repo is in maintenance mode.

## Use cases
- train an object detection model with pretrained backbones
- augment image datasets for training pipelines
- fine-tune image classification models in Keras
- run image segmentation with state-of-the-art models
- build multi-framework vision pipelines that switch between TensorFlow, JAX, and PyTorch
- generate images with stable diffusion in Keras

## When to choose
- you are already using Keras and need computer vision models or augmentations
- you want pretrained vision models that run on TensorFlow, JAX, or PyTorch backends
- you need production-grade training pipelines for detection or segmentation

## When to avoid
- you are starting a new project - use KerasHub instead since KerasCV is no longer actively developed
- you need frameworks outside the Keras ecosystem
- you need non-vision tasks like NLP or audio

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, computer-vision, data-science
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python, cross-platform
- tags: keras, tensorflow, jax, pytorch, data-augmentation, object-detection, image-segmentation, pretrained-models, keras-3, kerashub-migration

## Member repositories
- keras-team/keras-cv (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:24.245309+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:58:38.853799+00:00, confidence not recorded.
  - readme: https://github.com/keras-team/keras-cv (fetched 2026-08-28T04:03:24.245309+00:00, sha f97885a52a82)
  - registry_pypi: https://pypi.org/pypi/keras-cv/json (fetched 2026-08-29T13:00:24.862363+00:00, sha 1d9624fa8b8e)
- Data as of 2026-08-30T08:39:29.467469+00:00.