AltHub

keras-team/keras Alternatives

deep learning framework

Keras 3 is a multi-backend deep learning framework for building and training neural networks with a high-level API, supporting JAX, TensorFlow, PyTorch, and OpenVINO backends.

64.3kPythonApache-2.0active · last push 28d agoGitHub

Same job, different approach

Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.

tensorflow/tensorflowGitHub

Choose when you need a mature, low-level framework with a full ecosystem and production tooling; heavier than Keras.

An Open Source Machine Learning Framework for Everyone

198.0k
C++
Apache-2.0
active29d ago
pytorch/pytorchGitHub

Choose when you need dynamic, imperative programming with strong research community and lower-level control.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

102.7k
Python
NOASSERTION
active29d ago
tracel-ai/burnGitHub

Choose for Rust projects that need a modern deep learning framework with eager execution and portability.

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

15.8k
Rust
Apache-2.0
active29d ago
Oneflow-Inc/oneflowGitHub

Choose for large-scale distributed training with an alternative parallel architecture; less mature and smaller community.

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

9.4k
C++
Apache-2.0
slowing10mo ago
flashlight/flashlightGitHub

Choose for C++ projects needing a standalone ML library with high performance.

A C++ standalone library for machine learning

5.5k
C++
MIT
active3mo ago
deepjavalibrary/djlGitHub

Choose for JVM-based projects needing an engine-agnostic DL API.

An Engine-Agnostic Deep Learning Framework in Java

4.8k
Java
Apache-2.0
active29d ago
FluxML/Flux.jlGitHub

Choose for Julia projects wanting a differentiable programming DL framework.

Relax! Flux is the ML library that doesn't make you tensor

4.7k
Julia
NOASSERTION
active1mo ago
google-deepmind/dm-haikuGitHub

Choose when working directly in JAX and wanting a light, functional NN library instead of Keras's full API.

JAX-based neural network library

3.3k
Python
Apache-2.0
active1mo ago
mratsim/ArraymancerGitHub

Choose for Nim projects needing a tensor library with deep learning support and embedded/GPU targets.

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

1.4k
Nim
Apache-2.0
active4mo ago

Older generation, or narrower

An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.

apple/corenetGitHub

Choose for Apple's optimized CV models and training recipes, but it's narrower than Keras.

CoreNet: A library for training deep neural networks

7.0k
Jupyter Notebook
NOASSERTION
slowing1.0y ago
MegEngine/MegEngineGitHub

An older DL framework; choose if you need its distributed training features but note it's been stale for over a year.

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

4.8k
C++
Apache-2.0
dormant1.9y ago
chelsea0x3b/dfdxGitHub

Rust DL framework with compile-time shape checking; unmaintained since 2.1y.

Deep learning in Rust, with shape checked tensors and neural networks

1.9k
Rust
NOASSERTION
dormant2.2y ago
SciSharp/SiaNetGitHub

An older C# DL library; archived and unusable for production today.

An easy to use C# deep learning library with CUDA/OpenCL support

370
C#
MIT
archived7.3y ago
denosaurs/netsaurGitHub

An older Rust ML library with multi-backend support; unmaintained.

Powerful Powerful Machine Learning library with GPU, CPU and WASM backends

254
Rust
MIT
dormant2.0y ago
tensorpack/tensorpackGitHub

A previous-generation high-level training interface on TensorFlow; choose for legacy TF code.

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

6.3k
Python
Apache-2.0
dormant3.1y ago

Listed as an alternative to

These projects were analysed and named keras among their alternatives. The relationship is not symmetric — how keras rates them is a separate judgement, made when keras is analysed in its own right.

tensorflow/tfjsGitHub

calls keras “when you want the high-level Keras API directly in Python (on top of TensorFlow) rather than TF.js.”

A WebGL accelerated JavaScript library for training and deploying ML models.

19.1kTypeScriptactive
apple/corenetGitHub

calls keras “When you want a backend-agnostic high-level NN API instead of CoreNet's task-specific model zoo.”

CoreNet: A library for training deep neural networks

7.0kJupyter Notebookslowing