# keras-team/keras-applications

Reference implementations of popular deep learning models.

Repository: https://github.com/keras-team/keras-applications
Canonical: https://ross.abutalabs.com/products/keras-applications
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2022-02-17T22:37:33+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3015, "days_push": 1658, "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 1990, forks 883 (observed 2026-08-28T04:06:03.037684+00:00)

## What it is
Keras Applications provides reference implementations of popular deep learning models (e.g., ResNet, VGG, MobileNet) for use with Keras. The repository is deprecated, with all models moved into the core Keras repository and the TensorFlow pip package.

## Use cases
- use pretrained deep learning models like ResNet or MobileNet
- get reference implementations of popular neural network architectures
- apply transfer learning with pretrained Keras models
- classify images with off-the-shelf deep learning models

## When to choose
- you are on a legacy Keras/TensorFlow setup that still depends on the standalone keras-applications package
- you need the historical reference implementations for research or reproduction

## When to avoid
- you are starting a new project - use the models built into Keras (keras.io/api/applications) instead
- you need updates, bug fixes, or support - this repo is deprecated and unmaintained

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning
- domain: deep-learning, machine-learning, computer-vision
- platform: python
- tags: pretrained-models, keras, tensorflow, deprecated, reference-implementations

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.037684+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 2026-08-30T03:02:44.076221+00:00, confidence not recorded.
  - readme: https://github.com/keras-team/keras-applications (fetched 2026-08-28T04:06:03.037684+00:00, sha bd6b0a873867)
  - registry_pypi: https://pypi.org/pypi/keras-applications/json (fetched 2026-08-29T10:42:33.200034+00:00, sha 264564b2fe2f)
- Data as of 2026-08-30T08:39:29.467469+00:00.