Keras-Applications
Reference implementations of popular deep learning models
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires numpy and h5py; designed for Python 2.7–3.6 (older Python versions).
- 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.
License · maintenance · safety
MIT (permissive) — Distributed under the MIT license (permissive), which allows use in commercial and private projects with minimal restrictions.
last release 2019-05-30 (2633 days) · last repo commit 2022-02-17 · 1,990 stars · archived
0 known vulnerabilities (OSV.dev, 2026-08-14) · 5,024,199 downloads/mo, #2,180 on PyPI
Alternatives
Verify before relying
pip install keras-applications
from keras import applications
model = applications.VGG16(weights='imagenet')- 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.
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 on this page. Verify before relying on it.
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
keras-applications on PyPI
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.
Requires numpy and h5py; designed for Python 2.7–3.6 (older Python versions).
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')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 | Not specified |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesnumpyh5py |
| Maintenance | Abandoned 2,633 days since the last release |
| Last repo commit | repository archived |
| First released | |
| Downloads | 5,024,199 / month, #2,180 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 2Programming Language :: Python :: 2.7Programming Language :: Python :: 3Programming Language :: Python :: 3.6Topic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: Keras_Applications-1.0.8-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “pre-trained deep learning models”
- Keras-ApplicationsProvides pre-trained deep learning model definitions and weights for…
- openvino-devProvides command-line tools and Python APIs to convert deep learning…
- efficientnetProvides Keras and TensorFlow Keras implementations of EfficientNet,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Libraries packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
Provides parsing, arithmetic, and recurrence rule computation for dates and times, with timezone support and iCalendar RFC compliance.
Install it if you need to parse flexible date strings, compute relative dates, handle timezones, or work with recurrence rules—it's the de facto choice for these tasks.
Six provides utility functions to write Python code that runs on both Python 2.7 and Python 3.3+, smoothing over language differences between the two versions.
pytest is a testing framework that lets you write test functions using plain assert statements and automatically discovers and runs them, with detailed failure reporting.
See also pretrainedmodels · efficientnet · keras-hub · Keras-Preprocessing · scikeras · keras · pytorchcv · keras-nightly · face_recognition_models · keras-nlp