Alternatives To Keras
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Tensorflow177,889327774 hours ago46October 23, 20192,045apache-2.0C++
An Open Source Machine Learning Framework for Everyone
Transformers112,668641,8693 hours ago114July 18, 2023865apache-2.0Python
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Pytorch71,2303,3416,7284 hours ago37May 08, 202312,813otherPython
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Cs Video Courses60,439
21 hours ago2
List of Computer Science courses with video lectures.
Keras59,4475783 hours ago80June 27, 2023100apache-2.0Python
Deep Learning for humans
D2l Zh48,2731115 days ago47December 15, 202248apache-2.0Python
2 days ago23gpl-3.0Python
Deepfakes Software For All
Tensorflow Examples42,312
a year ago218otherJupyter Notebook
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
a month ago536gpl-3.0Python
DeepFaceLab is the leading software for creating deepfakes.
a day ago8September 21, 2021223agpl-3.0Python
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Alternatives To Keras
Select To Compare

Alternative Project Comparisons

Keras 3: A new multi-backend Keras

Keras 3 is a new multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.


Install with pip

Keras 3 is available as a preview release on PyPI named keras-core. Keras 2 (tf.keras) is distributed along with the tensorflow package.

  1. Install keras-core:
pip install keras-core
  1. Install backend package(s).

To use keras-core, you should also install the backend of choice: tensorflow, jax, or torch. Note that tensorflow is required for using certain Keras 3 features: certain preprocessing layers as well as pipelines.

Note: If you are using the keras-core package you also need to switch your Keras import. Use import keras_core as keras. This is a temporary step until the release of Keras 3 on PyPI.

Local installation

Keras 3 is compatible with Linux and MacOS systems. To install a local development version:

  1. Install dependencies:
pip install -r requirements.txt
  1. Run installation command from the root directory.
python --install
  1. Add accelerator support for the backend(s) of your choice.

The requirements.txt file will install a CPU-only version of TensorFlow, JAX, and PyTorch. Full instruction for installing tensorflow, jax, or torch with accelerator support can be found on the respective project websites.

Configuring your backend

You can export the environment variable KERAS_BACKEND or you can edit your local config file at ~/.keras/keras.json to configure your backend. Available backend options are: "tensorflow", "jax", "torch". Example:

export KERAS_BACKEND="jax"

In Colab, you can do:

import os
os.environ["KERAS_BACKEND"] = "jax"

import keras

Note: The backend must be configured before importing keras, and the backend cannot be changed after the package has been imported.

Backwards compatibility

Keras 3 is intended to work as a drop-in replacement for tf.keras (when using the TensorFlow backend). Just take your existing tf.keras code, make sure that your calls to are using the up-to-date .keras format, and you're done.

If your tf.keras model does not include custom components, you can start running it on top of JAX or PyTorch immediately.

If it does include custom components (e.g. custom layers or a custom train_step()), it is usually possible to convert it to a backend-agnostic implementation in just a few minutes.

In addition, Keras models can consume datasets in any format, regardless of the backend you're using: you can train your models with your existing pipelines or PyTorch DataLoaders.

Keras 3 timeline

At the moment, we are releasing Keras 3 as a preview release with under the keras-core name on PyPI. We encourage anyone interested in the future of the library to try it out and give feedback.

You can find the current stable release of Keras 2 at the tf-keras repository.

We will share updates on the release timeline as soon as they are available.

Why use Keras 3?

  • Run your high-level Keras workflows on top of any framework -- benefiting at will from the advantages of each framework, e.g. the scalability and performance of JAX or the production ecosystem options of TensorFlow.
  • Write custom components (e.g. layers, models, metrics) that you can use in low-level workflows in any framework.
    • You can take a Keras model and train it in a training loop written from scratch in native TF, JAX, or PyTorch.
    • You can take a Keras model and use it as part of a PyTorch-native Module or as part of a JAX-native model function.
  • Make your ML code future-proof by avoiding framework lock-in.
  • As a PyTorch user: get access to power and usability of Keras, at last!
  • As a JAX user: get access to a fully-featured, battle-tested, well-documented modeling and training library.
Popular Deep Learning Projects
Popular Machine Learning Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Machine Learning
Deep Learning
Neural Network
Data Science