![]() | |
Original author(s) | François Chollet |
---|---|
Developer(s) | ONEIROS |
Initial release | 27 March 2015 |
Stable release | 3.4.1 [1] / 26 June 2024 |
Repository | |
Written in | Python |
Platform | Cross-platform |
Type | Frontend for TensorFlow, JAX or PyTorch (and more) |
License | Apache 2.0 |
Website | keras![]() |
Keras is an open-source library that provides a Python interface for artificial neural networks. Keras was first independent software, then integrated into the TensorFlow library, and later supporting more. "Keras 3 is a full rewrite of Keras [and can be used] as a low-level cross-framework language to develop custom components such as layers, models, or metrics that can be used in native workflows in JAX, TensorFlow, or PyTorch — with one codebase." [2] Keras 3 will be the default Keras version for TensorFlow 2.16 onwards, but Keras 2 can still be used. [3]
The name 'Keras' derives from the Ancient Greek word κέρας (Keras) meaning 'horn'. [4]
Designed to enable fast experimentation with deep neural networks, Keras focuses on being user-friendly, modular, and extensible. It was developed as part of the research effort of project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System), [5] and its primary author and maintainer is François Chollet, a Google engineer. Chollet is also the author of the Xception deep neural network model. [6]
Up until version 2.3, Keras supported multiple backends, including TensorFlow, Microsoft Cognitive Toolkit, Theano, and PlaidML. [7] [8] [9]
As of version 2.4, only TensorFlow was supported. Starting with version 3.0 (as well as its preview version, Keras Core), however, Keras has become multi-backend again, supporting TensorFlow, JAX, and PyTorch. [10]
Keras contains numerous implementations of commonly used neural-network building blocks such as layers, objectives, activation functions, optimizers, and a host of tools for working with image and text data to simplify programming in deep neural network area. The code is hosted on GitHub, and community support forums include the GitHub issues page, and a Slack channel.[ citation needed ]
In addition to standard neural networks, Keras has support for convolutional and recurrent neural networks. It supports other common utility layers like dropout, batch normalization, and pooling. [11]
Keras allows users to produce deep models on smartphones (iOS and Android), on the web, or on the Java Virtual Machine. [8] It also allows use of distributed training of deep-learning models on clusters of graphics processing units (GPU) and tensor processing units (TPU). [12]
Theano is a Python library and optimizing compiler for manipulating and evaluating mathematical expressions, especially matrix-valued ones. In Theano, computations are expressed using a NumPy-esque syntax and compiled to run efficiently on either CPU or GPU architectures.
Torch is an open-source machine learning library, a scientific computing framework, and a scripting language based on Lua. It provides LuaJIT interfaces to deep learning algorithms implemented in C. It was created by the Idiap Research Institute at EPFL. Torch development moved in 2017 to PyTorch, a port of the library to Python.
Eclipse Deeplearning4j is a programming library written in Java for the Java virtual machine (JVM). It is a framework with wide support for deep learning algorithms. Deeplearning4j includes implementations of the restricted Boltzmann machine, deep belief net, deep autoencoder, stacked denoising autoencoder and recursive neural tensor network, word2vec, doc2vec, and GloVe. These algorithms all include distributed parallel versions that integrate with Apache Hadoop and Spark.
TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks.
The following table compares notable software frameworks, libraries and computer programs for deep learning.
Tensor Processing Unit (TPU) is an AI accelerator application-specific integrated circuit (ASIC) developed by Google for neural network machine learning, using Google's own TensorFlow software. Google began using TPUs internally in 2015, and in 2018 made them available for third-party use, both as part of its cloud infrastructure and by offering a smaller version of the chip for sale.
spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython. The library is published under the MIT license and its main developers are Matthew Honnibal and Ines Montani, the founders of the software company Explosion.
Caffe is a deep learning framework, originally developed at University of California, Berkeley. It is open source, under a BSD license. It is written in C++, with a Python interface.
PyTorch is a machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, originally developed by Meta AI and now part of the Linux Foundation umbrella. It is recognized as one of the two most popular machine learning libraries alongside TensorFlow, offering free and open-source software released under the modified BSD license. Although the Python interface is more polished and the primary focus of development, PyTorch also has a C++ interface.
ROCm is an Advanced Micro Devices (AMD) software stack for graphics processing unit (GPU) programming. ROCm spans several domains: general-purpose computing on graphics processing units (GPGPU), high performance computing (HPC), heterogeneous computing. It offers several programming models: HIP, OpenMP, and OpenCL.
In computer vision, SqueezeNet is the name of a deep neural network for image classification that was released in 2016. SqueezeNet was developed by researchers at DeepScale, University of California, Berkeley, and Stanford University. In designing SqueezeNet, the authors' goal was to create a smaller neural network with fewer parameters while achieving competitive accuracy.
PlaidML is a portable tensor compiler. Tensor compilers bridge the gap between the universal mathematical descriptions of deep learning operations, such as convolution, and the platform and chip-specific code needed to perform those operations with good performance. Internally, PlaidML makes use of the Tile eDSL to generate OpenCL, OpenGL, LLVM, or CUDA code. It enables deep learning on devices where the available computing hardware is either not well supported or the available software stack contains only proprietary components. For example, it does not require the usage of CUDA or cuDNN on Nvidia hardware, while achieving comparable performance.
Dask is an open-source Python library for parallel computing. Dask scales Python code from multi-core local machines to large distributed clusters in the cloud. Dask provides a familiar user interface by mirroring the APIs of other libraries in the PyData ecosystem including: Pandas, scikit-learn and NumPy. It also exposes low-level APIs that help programmers run custom algorithms in parallel.
Flux is an open-source machine-learning software library and ecosystem written in Julia. Its current stable release is v0.14.5 . It has a layer-stacking-based interface for simpler models, and has a strong support on interoperability with other Julia packages instead of a monolithic design. For example, GPU support is implemented transparently by CuArrays.jl. This is in contrast to some other machine learning frameworks which are implemented in other languages with Julia bindings, such as TensorFlow.jl, and thus are more limited by the functionality present in the underlying implementation, which is often in C or C++. Flux joined NumFOCUS as an affiliated project in December of 2021.
fast.ai is a non-profit research group focused on deep learning and artificial intelligence. It was founded in 2016 by Jeremy Howard and Rachel Thomas with the goal of democratizing deep learning. They do this by providing a massive open online course (MOOC) named "Practical Deep Learning for Coders," which has no other prerequisites except for knowledge of the programming language Python.
NNI is a free and open-source AutoML toolkit developed by Microsoft. It is used to automate feature engineering, model compression, neural architecture search, and hyper-parameter tuning.
Owl Scientific Computing is a software system for scientific and engineering computing developed in the Department of Computer Science and Technology, University of Cambridge. The System Research Group (SRG) in the department recognises Owl as one of the representative systems developed in SRG in the 2010s. The source code is licensed under the MIT License and can be accessed from the GitHub repository.
A graph neural network (GNN) belongs to a class of artificial neural networks for processing data that can be represented as graphs.
CuPy is an open source library for GPU-accelerated computing with Python programming language, providing support for multi-dimensional arrays, sparse matrices, and a variety of numerical algorithms implemented on top of them. CuPy shares the same API set as NumPy and SciPy, allowing it to be a drop-in replacement to run NumPy/SciPy code on GPU. CuPy supports Nvidia CUDA GPU platform, and AMD ROCm GPU platform starting in v9.0.
Google JAX is a machine learning framework for transforming numerical functions to be used in Python. It is described as bringing together a modified version of autograd and TensorFlow's XLA. It is designed to follow the structure and workflow of NumPy as closely as possible and works with various existing frameworks such as TensorFlow and PyTorch. The primary functions of JAX are: