---
id: keras-applications
version: "1.0.8"
license: MIT
license_treatment: permissive
maintenance: abandoned
---

# Keras-Applications — Reference implementations of popular deep learning models

License: permissive · Maintenance: abandoned · Downloads: 5.0M/mo

## What it is and what it does

Keras Applications is a standalone module that bundles reference implementations of popular deep learning architectures (VGG16, ResNet50, Xception, MobileNet, and others) along with pre-trained weights, typically trained on ImageNet. It is designed to be imported directly from Keras and used for transfer learning or as a starting point for custom models.

The package is now abandoned—its repository was archived and the last commit was in February 2022. While it remains widely downloaded and carries no known vulnerabilities, it receives no active maintenance or updates. Developers should verify whether modern Keras or TensorFlow distributions include these models natively, as this standalone package may no longer be the canonical source.

Use it for:

- Load a pre-trained VGG16 or ResNet50 model for image classification without training from scratch.
- Extract features from images using a pre-trained architecture as a backbone for transfer learning.
- Quickly prototype a computer vision model by starting with a well-known architecture and pre-trained weights.
- Fine-tune a pre-trained model on a custom dataset for domain-specific image recognition tasks.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Provides pre-trained deep learning model definitions and weights for architectures like VGG16, ResNet50, Xception, and MobileNet, ready to use with Keras.

No—not recommended for new projects. The package is abandoned (last update 2019, repository archived 2022) and targets Python 2.7–3.6, which are now obsolete. Modern Keras and TensorFlow distributions include these models natively. Install only if you are maintaining legacy code that explicitly depends on this package.

## Install

pip install keras-applications
uv add keras-applications
poetry add keras-applications

## Installing Keras-Applications

Before you install: Low install friction with only two runtime dependencies (numpy and h5py). However, the package is abandoned—last commit was 2022-02-17 and the repository is archived. It remains in the top 5000 by downloads but receives no active maintenance.

License in practice: Distributed under the MIT license (permissive), which allows use in commercial and private projects with minimal restrictions.

Quickstart:

pip install keras-applications

from keras import applications
model = applications.VGG16(weights='imagenet')

Requires numpy and h5py; designed for Python 2.7–3.6 (older Python versions).

Verify before relying:

- Whether pre-trained weights are still available or if download endpoints have changed since abandonment.
- Compatibility with modern Keras/TensorFlow versions beyond the stated Python 3.6 support.
- Whether this package is still the recommended way to access these models in current Keras distributions.

## Package facts

- License: MIT (permissive)
- Python support: unspecified
- Install friction: low
- Maintenance: abandoned
- Downloads: 5.0M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

pre-trained deep learning models, keras model architectures, vgg resnet xception mobilenet, transfer learning models, neural network model weights, image classification architectures, keras applications module, deep-learning, transfer-learning, abandoned

[View on SkillFed](https://skillfed.io/packages/keras-applications) · [View on PyPI](https://pypi.org/project/keras-applications/)