TensorFlow for machine learning

TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.

You are bound to have already used machine learning features created with TensorFlow without even realising it. For example, if you use Gmail you will have recently noticed that as you type you are shown auto sentence completion text to save typing. This becaused of the so called "Smart Compose" machine learning feature which provides real-time suggestions in Gmail that assists users in writing emails by reducing repetitive typing. At the core of Smart Compose is a large-scale neural language model. Google leveraged TensorFlow for state-of-the-art machine learning techniques for language model training which enabled high-quality suggestion prediction, and constructed novel serving infrastructure for high-throughput and real-time inference.

Thousands of other companies harness TensorFlow for machine learning and you may have already experienced this with Airbnb using TensorFlow to classify images, PayPal using TensorFlow for fraud detection by identifying fraud patterns, Spotify using TensorFlow to personalise recommendations and Twitter using TensorFlow to build their "Ranked Timeline" so users don't miss their most important tweets even if they follow thousands of users.

Easy model building
TensorFlow offers multiple levels of abstraction so you can choose the right one for your needs. Build and train models by using the high-level Keras API, which makes getting started with TensorFlow and machine learning easy.

If you need more flexibility, eager execution allows for immediate iteration and intuitive debugging. For large ML training tasks, use the Distribution Strategy API for distributed training on different hardware configurations without changing the model definition.

Robust ML production anywhere
TensorFlow has always provided a direct path to production. Whether it’s on servers, edge devices, or the web, TensorFlow lets you train and deploy your model easily, no matter what language or platform you use.

Use TensorFlow Extended (TFX) if you need a full production ML pipeline. For running inference on mobile and edge devices, use TensorFlow Lite. Train and deploy models in JavaScript environments using TensorFlow.js.

Powerful experimentation for research
Build and train state-of-the-art models without sacrificing speed or performance. TensorFlow gives you the flexibility and control with features like the Keras Functional API and Model Subclassing API for creation of complex topologies. For easy prototyping and fast debugging, use eager execution.

TensorFlow also supports an ecosystem of powerful add-on libraries and models to experiment with, including Ragged Tensors, TensorFlow Probability, Tensor2Tensor and BERT.

TensorFlow Hub
A comprehensive repository of trained models ready for fine-tuning and deployable anywhere.

Model Garden
Machine learning models and examples built with TensorFlow's high-level APIs.

TensorFlow.js models
Pre-trained machine learning models ready-to-use in the web browser on the client side, or anywhere that JavaScript can run such as Node.js.

TensorFlow official datasets
A collection of datasets ready to use with TensorFlow.

Google research datasets
Explore large-scale datasets released by Google research teams in a wide range of computer science disciplines.

Colaboratory is a free Jupyter notebook environment that requires no setup and runs entirely in the cloud, allowing you to execute TensorFlow code in your browser with a single click.

A suite of visualization tools to understand, debug, and optimize TensorFlow programs.

What-If Tool
A tool for code-free probing of machine learning models, useful for model understanding, debugging, and fairness. Available in TensorBoard and jupyter or colab notebooks.

ML Perf
A broad ML benchmark suite for measuring performance of ML software frameworks, ML hardware accelerators, and ML cloud platforms.

XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes TensorFlow computations. The results are improvements in speed, memory usage, and portability on server and mobile platforms.

TensorFlow Playground
Tinker with a neural network in your browser. Don’t worry, you can’t break it.

TPU Research Cloud
The TPU Research Cloud (TRC) program enables researchers to apply for access to a cluster of more than 1,000 Cloud TPUs at no charge to help them accelerate the next wave of research breakthroughs.

A new intermediate representation and compiler framework.

TensorFlow Hub
A library for reusable machine learning. Download and reuse the latest trained models with a minimal amount of code.

Model Optimization
The TensorFlow Model Optimization Toolkit is a suite of tools for optimizing ML models for deployment and execution.

TensorFlow Recommenders
A library for building recommender system models.

A library for flexible, controlled and interpretable ML solutions with common-sense shape constraints.

TensorFlow Graphics
A library of computer graphics functionalities ranging from cameras, lights, and materials to renderers.

TensorFlow Federated
An open source framework for machine learning and other computations on decentralized data.

TensorFlow Probability is a library for probabilistic reasoning and statistical analysis.

Tensor2Tensor is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

TensorFlow Privacy
A Python library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy.

TensorFlow Agents
A library for reinforcement learning in TensorFlow.

A research framework for fast prototyping of reinforcement learning algorithms.

TRFL (pronounced “truffle”) is a library for reinforcement learning building blocks created by DeepMind.

Mesh TensorFlow
A language for distributed deep learning, capable of specifying a broad class of distributed tensor computations.

Makes it easy to store and manipulate data with non-uniform shape, including text (words, sentences, characters), and batches of variable length.

Unicode Ops
Supports working with Unicode text directly in TensorFlow.

TensorFlow Ranking
TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform.

Magenta is a research project exploring the role of machine learning in the process of creating art and music.

Nucleus is a library of Python and C++ code designed to make it easy to read, write and analyze data in common genomics file formats like SAM and VCF.

A library from DeepMind for constructing neural networks.

Neural Structured Learning
A learning framework to train neural networks by leveraging structured signals in addition to feature inputs.

TensorFlow Addons
Extra functionality for TensorFlow, maintained by SIG Addons.

TensorFlow I/O
Dataset, streaming, and file system extensions, maintained by SIG IO.

TensorFlow Quantum
TensorFlow Quantum is a quantum machine learning library for rapid prototyping of hybrid quantum-classical ML models.

Model Card Toolkit
Streamline and generate Model Cards—machine learning documents that provide context and transparency into a model's development and performance.

Model Remediation
A library to help create and train models in a way that reduces or eliminates user harm resulting from underlying performance biases.

Fairness Indicators
A library that enables easy computation of commonly-identified fairness metrics for binary and multiclass classifiers.

TensorFlow Cloud is a library to connect your local environment to Google Cloud.

Decision Forests
State-of-the-art algorithms for training, serving and interpreting models that use decision forests for classification, regression and ranking.

TensorFlow Text
A collection of text- and NLP-related classes and ops