TensorFlow is a

free and open-source Free and open-source software (FOSS) is a term used to refer to groups of software consisting of both free software and open-source software where anyone is freely licensed to use, copy, study, and change the software in any way, and the source ...

software library In computer science, a library is a collection of non-volatile resources used by computer programs, often for software development. These may include configuration data, documentation, help data, message templates, pre-written code and sub ...

for

machine learning Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine ...

and

artificial intelligence Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech r ...

. It can be used across a range of tasks but has a particular focus on

training Training is teaching, or developing in oneself or others, any skills and knowledge or fitness that relate to specific useful competencies. Training has specific goals of improving one's capability, capacity, productivity and performance. I ...

and

inference Inferences are steps in reasoning, moving from premises to logical consequences; etymologically, the word '' infer'' means to "carry forward". Inference is theoretically traditionally divided into deduction and induction, a distinction that ...

deep neural networks Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. ...

. "It is machine learning software being used for various kinds of perceptual and language understanding tasks" – Jeffrey Dean, minute 0:47 / 2:17 from YouTube clip TensorFlow was developed by the

Google Brain Google Brain is a deep learning artificial intelligence research team under the umbrella of Google AI, a research division at Google dedicated to artificial intelligence. Formed in 2011, Google Brain combines open-ended machine learning research ...

team for internal

Google Google LLC () is an American Multinational corporation, multinational technology company focusing on Search Engine, search engine technology, online advertising, cloud computing, software, computer software, quantum computing, e-commerce, ar ...

use in research and production. The initial version was released under the Apache License 2.0 in 2015. Google released the updated version of TensorFlow, named TensorFlow 2.0, in September 2019. TensorFlow can be used in a wide variety of programming languages, including Python,

JavaScript JavaScript (), often abbreviated as JS, is a programming language that is one of the core technologies of the World Wide Web, alongside HTML and CSS. As of 2022, 98% of Website, websites use JavaScript on the Client (computing), client side ...

, C++, and

Java Java (; id, Jawa, ; jv, ꦗꦮ; su, ) is one of the Greater Sunda Islands in Indonesia. It is bordered by the Indian Ocean to the south and the Java Sea to the north. With a population of 151.6 million people, Java is the world's mo ...

. This flexibility lends itself to a range of applications in many different sectors.

History

DistBelief

Starting in 2011, Google Brain built DistBelief as a proprietary

system based on deep learning

neural networks A neural network is a network or circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up of biological ...

. Its use grew rapidly across diverse

Alphabet An alphabet is a standardized set of basic written graphemes (called letters) that represent the phonemes of certain spoken languages. Not all writing systems represent language in this way; in a syllabary, each character represents a s ...

companies in both research and commercial applications. Google assigned multiple computer scientists, including

Jeff Dean Jeffrey Adgate "Jeff" Dean (born July 23, 1968) is an American computer scientist and software engineer. Since 2018, he is the lead of Google AI, Google's AI division. Education Dean received a B.S., ''summa cum laude'', from the University ...

, to simplify and refactor the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow. In 2009, the team, led by

Geoffrey Hinton Geoffrey Everest Hinton One or more of the preceding sentences incorporates text from the royalsociety.org website where: (born 6 December 1947) is a British-Canadian cognitive psychologist and computer scientist, most noted for his work on ...

, had implemented generalized

backpropagation In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...

and other improvements which allowed generation of

neural network A neural network is a network or neural circuit, circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up ...

s with substantially higher accuracy, for instance a 25% reduction in errors in

speech recognition Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ma ...

TensorFlow

TensorFlow is Google Brain's second-generation system. Version 1.0.0 was released on February 11, 2017. While the

reference implementation In the software development process, a reference implementation (or, less frequently, sample implementation or model implementation) is a program that implements all requirements from a corresponding specification. The reference implementation ...

runs on single devices, TensorFlow can run on multiple CPUs and

GPU A graphics processing unit (GPU) is a specialized electronic circuit designed to manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device. GPUs are used in embedded systems, mob ...

s (with optional

CUDA CUDA (or Compute Unified Device Architecture) is a parallel computing platform and application programming interface (API) that allows software to use certain types of graphics processing units (GPUs) for general purpose processing, an approach ...

and

SYCL SYCL is a higher-level programming model to improve programming productivity on various hardware accelerators. It is a single-source embedded domain-specific language (eDSL) based on pure C++17. It is a standard developed by Khronos Group, anno ...

extensions for

general-purpose computing on graphics processing units General-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditiona ...

). TensorFlow is available on 64-bit

Linux Linux ( or ) is a family of open-source Unix-like operating systems based on the Linux kernel, an operating system kernel first released on September 17, 1991, by Linus Torvalds. Linux is typically packaged as a Linux distribution, which i ...

macOS macOS (; previously OS X and originally Mac OS X) is a Unix operating system developed and marketed by Apple Inc. since 2001. It is the primary operating system for Apple's Mac (computer), Mac computers. Within the market of ...

Windows Windows is a group of several proprietary graphical operating system families developed and marketed by Microsoft. Each family caters to a certain sector of the computing industry. For example, Windows NT for consumers, Windows Server for ...

, and mobile computing platforms including Android and

iOS iOS (formerly iPhone OS) is a mobile operating system created and developed by Apple Inc. exclusively for its hardware. It is the operating system that powers many of the company's mobile devices, including the iPhone; the term also include ...

. Its flexible architecture allows for the easy deployment of computation across a variety of platforms (CPUs, GPUs, TPUs), and from desktops to clusters of servers to mobile and edge devices. TensorFlow computations are expressed as stateful

dataflow In computing, dataflow is a broad concept, which has various meanings depending on the application and context. In the context of software architecture, data flow relates to stream processing or reactive programming. Software architecture Da ...

graphs Graph may refer to: Mathematics *Graph (discrete mathematics), a structure made of vertices and edges **Graph theory, the study of such graphs and their properties * Graph (topology), a topological space resembling a graph in the sense of discr ...

. The name TensorFlow derives from the operations that such neural networks perform on multidimensional data arrays, which are referred to as ''

tensor In mathematics, a tensor is an algebraic object that describes a multilinear relationship between sets of algebraic objects related to a vector space. Tensors may map between different objects such as vectors, scalars, and even other tens ...

s''. During the Google I/O Conference in June 2016, Jeff Dean stated that 1,500 repositories on

GitHub GitHub, Inc. () is an Internet hosting service for software development and version control using Git. It provides the distributed version control of Git plus access control, bug tracking, software feature requests, task management, co ...

mentioned TensorFlow, of which only 5 were from Google. Machine Learning: Google I/O 2016 Minute 07:30/44:44
accessdate=2016-06-05 In December 2017, developers from Google, Cisco, RedHat, CoreOS, and CaiCloud introduced Kubeflow at a conference. Kubeflow allows operation and deployment of TensorFlow on

Kubernetes Kubernetes (, commonly stylized as K8s) is an open-source container orchestration system for automating software deployment, scaling, and management. Google originally designed Kubernetes, but the Cloud Native Computing Foundation now maintai ...

. In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in

. In Jan 2019, Google announced TensorFlow 2.0. It became officially available in Sep 2019. In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics.

Tensor processing unit (TPU)

In May 2016, Google announced its

Tensor processing unit 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 ...

(TPU), an

application-specific integrated circuit An application-specific integrated circuit (ASIC ) is an integrated circuit (IC) chip customized for a particular use, rather than intended for general-purpose use, such as a chip designed to run in a digital voice recorder or a high-effici ...

(ASIC, a hardware chip) built specifically for

and tailored for TensorFlow. A TPU is a programmable

AI accelerator An AI accelerator is a class of specialized hardware accelerator or computer system designed to accelerate artificial intelligence and machine learning applications, including artificial neural networks and machine vision. Typical applications ...

designed to provide high

throughput Network throughput (or just throughput, when in context) refers to the rate of message delivery over a communication channel, such as Ethernet or packet radio, in a communication network. The data that these messages contain may be delivered ov ...

of low-precision

arithmetic Arithmetic () is an elementary part of mathematics that consists of the study of the properties of the traditional operations on numbers—addition, subtraction, multiplication, division, exponentiation, and extraction of roots. In the 19th c ...

(e.g.,

8-bit In computer architecture, 8-bit integers or other data units are those that are 8 bits wide (1 octet). Also, 8-bit central processing unit (CPU) and arithmetic logic unit (ALU) architectures are those that are based on registers or data buses of ...

), and oriented toward using or running models rather than

them. Google announced they had been running TPUs inside their data centers for more than a year, and had found them to deliver an

order of magnitude An order of magnitude is an approximation of the logarithm of a value relative to some contextually understood reference value, usually 10, interpreted as the base of the logarithm and the representative of values of magnitude one. Logarithmic di ...

better-optimized

performance per watt In computing, performance per watt is a measure of the energy efficiency of a particular computer architecture or computer hardware. Literally, it measures the rate of computation that can be delivered by a computer for every watt of power consu ...

for machine learning. In May 2017, Google announced the second-generation, as well as the availability of the TPUs in

Google Compute Engine Google Compute Engine (GCE) is the Infrastructure as a Service (IaaS) component of Google Cloud Platform which is built on the global infrastructure that runs Google's search engine, Gmail, YouTube and other services. Google Compute Engine enab ...

. The second-generation TPUs deliver up to 180 teraflops of performance, and when organized into clusters of 64 TPUs, provide up to 11.5 petaflops. In May 2018, Google announced the third-generation TPUs delivering up to 420 teraflops of performance and 128 GB high bandwidth memory (HBM). Cloud TPU v3 Pods offer 100+ petaflops of performance and 32 TB HBM. In February 2018, Google announced that they were making TPUs available in beta on the Google Cloud Platform.

Edge TPU

In July 2018, the Edge TPU was announced. Edge TPU is Google's purpose-built

ASIC An application-specific integrated circuit (ASIC ) is an integrated circuit (IC) chip customized for a particular use, rather than intended for general-purpose use, such as a chip designed to run in a digital voice recorder or a high-effici ...

chip designed to run TensorFlow Lite machine learning (ML) models on small client computing devices such as smartphones known as edge computing.

TensorFlow Lite

In May 2017, Google announced a software stack specifically for mobile development, TensorFlow Lite. In January 2019, TensorFlow team released a developer preview of the mobile GPU inference engine with OpenGL ES 3.1 Compute Shaders on Android devices and Metal Compute Shaders on iOS devices. In May 2019, Google announced that their TensorFlow Lite Micro (also known as TensorFlow Lite for Microcontrollers) and ARM's uTensor would be merging.

Pixel Visual Core (PVC)

In October 2017, Google released the Google Pixel 2 which featured their

Pixel Visual Core The Pixel Visual Core (PVC) is a series of ARM-based system in package (SiP) image processors designed by Google. The PVC is a fully programmable image, vision and AI multi-core domain-specific architecture (DSA) for mobile devices and in future ...

(PVC), a fully programmable

image An image is a visual representation of something. It can be two-dimensional, three-dimensional, or somehow otherwise feed into the visual system to convey information. An image can be an artifact, such as a photograph or other two-dimensio ...

vision Vision, Visions, or The Vision may refer to: Perception Optical perception * Visual perception, the sense of sight * Visual system, the physical mechanism of eyesight * Computer vision, a field dealing with how computers can be made to gain und ...

and AI processor for mobile devices. The PVC supports TensorFlow for machine learning (and

Halide In chemistry, a halide (rarely halogenide) is a binary chemical compound, of which one part is a halogen atom and the other part is an element or radical that is less electronegative (or more electropositive) than the halogen, to make a f ...

for image processing).

TensorFlow 2.0

As TensorFlow's market share among research papers was declining to the advantage of

PyTorch PyTorch is a machine learning framework 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 free and op ...

, the TensorFlow Team announced a release of a new major version of the library in September 2019. TensorFlow 2.0 introduced many changes, the most significant being TensorFlow eager, which changed the automatic differentiation scheme from the static computational graph, to the "Define-by-Run" scheme originally made popular by

Chainer Chainer is an open source deep learning framework written purely in Python on top of NumPy and CuPy Python libraries. The development is led by Japanese venture company Preferred Networks in partnership with IBM, Intel, Microsoft, and Nvidia. ...

and later

. Other major changes included removal of old libraries, cross-compatibility between trained models on different versions of TensorFlow, and significant improvements to the performance on GPU.

Features

AutoDifferentiation

AutoDifferentiation is the process of automatically calculating the gradient vector of a model with respect to each of its parameters. With this feature, TensorFlow can automatically compute the gradients for the parameters in a model, which is useful to algorithms such as

which require gradients to optimize performance. To do so, the framework must keep track of the order of operations done to the input Tensors in a model, and then compute the gradients with respect to the appropriate parameters.

Eager execution

TensorFlow includes an “eager execution” mode, which means that operations are evaluated immediately as opposed to being added to a computational graph which is executed later. Code executed eagerly can be examined step-by step-through a debugger, since data is augmented at each line of code rather than later in a computational graph. This execution paradigm is considered to be easier to debug because of its step by step transparency.

Distribute

In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies. This

distributed computing A distributed system is a system whose components are located on different networked computers, which communicate and coordinate their actions by passing messages to one another from any system. Distributed computing is a field of computer sci ...

can often speed up the execution of training and evaluating of TensorFlow models and is a common practice in the field of AI.

Losses

To train and assess models, TensorFlow provides a set of

loss function In mathematical optimization and decision theory, a loss function or cost function (sometimes also called an error function) is a function that maps an event or values of one or more variables onto a real number intuitively representing some "co ...

s (also known as cost functions). Some popular examples include

mean squared error In statistics, the mean squared error (MSE) or mean squared deviation (MSD) of an estimator (of a procedure for estimating an unobserved quantity) measures the average of the squares of the errors—that is, the average squared difference betwe ...

(MSE) and binary cross entropy (BCE). These loss functions compute the “error” or “difference” between a model's output and the expected output (more broadly, the difference between two tensors). For different datasets and models, different losses are used to prioritize certain aspects of performance.

Metrics

In order to assess the performance of machine learning models, TensorFlow gives API access to commonly used metrics. Examples include various accuracy metrics (binary, categorical, sparse categorical) along with other metrics such as Precision, Recall, and Intersection-over-Union (IoU).

TF.nn

TensorFlow.nn is a module for executing primitive

operations on models. Some of these operations include variations of

convolutions In mathematics (in particular, functional analysis), convolution is a mathematical operation on two functions ( and ) that produces a third function (f*g) that expresses how the shape of one is modified by the other. The term ''convolution'' ...

(1/2/3D, Atrous, depthwise),

activation function In artificial neural networks, the activation function of a node defines the output of that node given an input or set of inputs. A standard integrated circuit can be seen as a digital network of activation functions that can be "ON" (1) or " ...

s (

Softmax The softmax function, also known as softargmax or normalized exponential function, converts a vector of real numbers into a probability distribution of possible outcomes. It is a generalization of the logistic function to multiple dimensions, a ...

, RELU, GELU, Sigmoid, etc.) and their variations, and other Tensor operations ( max-pooling, bias-add, etc.).

Optimizers

TensorFlow offers a set of optimizers for training neural networks, including

ADAM Adam; el, Ἀδάμ, Adám; la, Adam is the name given in Genesis 1-5 to the first human. Beyond its use as the name of the first man, ''adam'' is also used in the Bible as a pronoun, individually as "a human" and in a collective sense as " ...

, ADAGRAD, and

Stochastic Gradient Descent Stochastic gradient descent (often abbreviated SGD) is an iterative method for optimizing an objective function with suitable smoothness properties (e.g. differentiable or subdifferentiable). It can be regarded as a stochastic approximation of ...

(SGD). When training a model, different optimizers offer different modes of parameter tuning, often affecting a model's convergence and performance.

Usage and extensions

TensorFlow

TensorFlow serves as the core platform and library for machine learning. TensorFlow's APIs use

Keras Keras is an open-source software library that provides a Python interface for artificial neural networks. Keras acts as an interface for the TensorFlow library. Up until version 2.3, Keras supported multiple backends, including TensorFlow, M ...

to allow users to make their own machine learning models. In addition to building and training their model, TensorFlow can also help load the data to train the model, and deploy it using TensorFlow Serving. TensorFlow provides a stable Python API, as well as APIs without backwards compatibility guarantee for

Javascript JavaScript (), often abbreviated as JS, is a programming language that is one of the core technologies of the World Wide Web, alongside HTML and CSS. As of 2022, 98% of Website, websites use JavaScript on the Client (computing), client side ...

, C++, and

. Third-party language binding packages are also available for C#,

Haskell Haskell () is a general-purpose, statically-typed, purely functional programming language with type inference and lazy evaluation. Designed for teaching, research and industrial applications, Haskell has pioneered a number of programming lan ...

Julia Julia is usually a feminine given name. It is a Latinate feminine form of the name Julio and Julius. (For further details on etymology, see the Wiktionary entry "Julius".) The given name ''Julia'' had been in use throughout Late Antiquity (e ...

MATLAB MATLAB (an abbreviation of "MATrix LABoratory") is a proprietary multi-paradigm programming language and numeric computing environment developed by MathWorks. MATLAB allows matrix manipulations, plotting of functions and data, implementa ...

, R, Scala,

Rust Rust is an iron oxide, a usually reddish-brown oxide formed by the reaction of iron and oxygen in the catalytic presence of water or air moisture. Rust consists of hydrous iron(III) oxides (Fe2O3·nH2O) and iron(III) oxide-hydroxide (FeO(OH), ...

OCaml OCaml ( , formerly Objective Caml) is a general-purpose, multi-paradigm programming language which extends the Caml dialect of ML with object-oriented features. OCaml was created in 1996 by Xavier Leroy, Jérôme Vouillon, Damien Doligez, D ...

, and

Crystal A crystal or crystalline solid is a solid material whose constituents (such as atoms, molecules, or ions) are arranged in a highly ordered microscopic structure, forming a crystal lattice that extends in all directions. In addition, macr ...

. Bindings that are now archived and unsupported include Go and

Swift Swift or SWIFT most commonly refers to: * SWIFT, an international organization facilitating transactions between banks ** SWIFT code * Swift (programming language) * Swift (bird), a family of birds It may also refer to: Organizations * SWIFT ...

TensorFlow.js

TensorFlow also has a library for machine learning in JavaScript. Using the provided JavaScript APIs, TensorFlow.js allows users to use either Tensorflow.js models or converted models from TensorFlow or TFLite, retrain the given models, and run on the web.

TFLite

TensorFlow Lite has APIs for mobile apps or embedded devices to generate and deploy TensorFlow models. These models are compressed and optimized in order to be more efficient and have a higher performance on smaller capacity devices. TensorFlow Lite uses

FlatBuffers FlatBuffers is a free software library implementing a serialization format similar to Protocol Buffers, Thrift, Apache Avro, SBE, and Cap'n Proto, primarily written by Wouter van Oortmerssen and open-sourced by Google. It supports “zero-copy ...

as the data serialization format for network models, eschewing the

Protocol Buffers Protocol Buffers (Protobuf) is a free and open-source cross-platform data format used to serialize structured data. It is useful in developing programs to communicate with each other over a network or for storing data. The method involves an inte ...

format used by standard TensorFlow models.

TFX

TensorFlow Extended (abbrev. TFX) provides numerous components to perform all the operations needed for end-to-end production. Components include loading, validating, and transforming data, tuning, training, and evaluating the machine learning model, and pushing the model itself into production.

Integrations

Numpy

Numpy is one of the most popular Python data libraries, and TensorFlow offers integration and compatibility with its data structures. Numpy NDarrays, the library's native datatype, are automatically converted to TensorFlow Tensors in TF operations; the same is also true vice versa. This allows for the two libraries to work in unison without requiring the user to write explicit data conversions. Moreover, the integration extends to memory optimization by having TF Tensors share the underlying memory representations of Numpy NDarrays whenever possible.

Extensions

TensorFlow also offers a variety of libraries and extensions to advance and extend the models and methods used. For example, TensorFlow Recommenders and TensorFlow Graphics are libraries for their respective functionalities in recommendation systems and graphics, TensorFlow Federated provides a framework for decentralized data, and TensorFlow Cloud allows users to directly interact with Google Cloud to integrate their local code to Google Cloud. Other add-ons, libraries, and frameworks include TensorFlow Model Optimization, TensorFlow Probability, TensorFlow Quantum, and TensorFlow Decision Forests.

Google Colab

Google also released Colaboratory, a TensorFlow Jupyter notebook environment that does not require any setup. It runs on Google Cloud and allows users free access to GPUs and the ability to store and share notebooks on Google Drive.

Google JAX

Google JAX is a machine learning framework for transforming numerical functions. It is described as bringing together a modified version o
autograd
(automatic obtaining of the gradient function through differentiation of a function) and TensorFlow'
XLA
(Accelerated Linear Algebra). It is designed to follow the structure and workflow of NumPy as closely as possible and works with TensorFlow as well as other frameworks such as

. The primary functions of JAX are: # grad: automatic differentiation # jit: compilation # vmap: auto-vectorization # pmap: SPMD programming

Applications

Medical

GE Healthcare GE HealthCare is a subsidiary of American multinational conglomerate General Electric incorporated in New York and headquartered in Chicago, Illinois. As of 2017, it is a manufacturer and distributor of diagnostic imaging agents and radiopharma ...

used TensorFlow to increase the speed and accuracy of

MRIs Magnetic resonance imaging (MRI) is a medical imaging technique used in radiology to form pictures of the anatomy and the physiological processes inside the body. MRI scanners use strong magnetic fields, magnetic field gradients, and radio ...

in identifying specific body parts. Google used TensorFlow to create DermAssist, a free mobile application that allows users to take pictures of their skin and identify potential health complications. Sinovation Ventures used TensorFlow to identify and classify eye diseases from

optical coherence tomography Optical coherence tomography (OCT) is an imaging technique that uses low-coherence light to capture micrometer-resolution, two- and three-dimensional images from within optical scattering media (e.g., biological tissue). It is used for medic ...

(OCT) scans.

Social media

Twitter Twitter is an online social media and social networking service owned and operated by American company Twitter, Inc., on which users post and interact with 280-character-long messages known as "tweets". Registered users can post, like, and ...

implemented TensorFlow to rank tweets by importance for a given user, and changed their platform to show tweets in order of this ranking. Previously, tweets were simply shown in reverse chronological order. The photo sharing app

VSCO VSCO (), formerly known as VSCO Cam, is a photography mobile app for iOS and Android devices. The app was created by Joel Flory and Greg Lutze. The VSCO app allows users to capture photos in the app and edit them, using preset filters and editin ...

used TensorFlow to help suggest custom filters for photos.

Search Engine

officially released

RankBrain RankBrain is a machine learning-based search engine algorithm, the use of which was confirmed by Google on 26 October 2015. It helps Google to process search results and provide more relevant search results for users. In a 2015 interview, Google co ...

on October 26, 2015, backed by TensorFlow.

Education

InSpace, a virtual learning platform, used TensorFlow to filter out toxic chat messages in classrooms. Liulishuo, an online English learning platform, utilized TensorFlow to create an adaptive curriculum for each student. TensorFlow was used to accurately assess a student's current abilities, and also helped decide the best future content to show based on those capabilities.

Retail

The e-commerce platform Carousell used TensorFlow to provide personalized recommendations for customers. The cosmetics company ModiFace used TensorFlow to create an augmented reality experience for customers to test various shades of make-up on their face.

Research

TensorFlow is the foundation for the automated image-captioning software DeepDream.

Bibliography

* * * * *

External links

*
Learning TensorFlow.js Book (ENG)

References

{{Reflist Deep learning software Free software programmed in C++ Free software programmed in Python Free statistical software Google software Open-source artificial intelligence Python (programming language) scientific libraries Software using the Apache license 2015 software

History

DistBelief

TensorFlow

Tensor processing unit (TPU)

Edge TPU

TensorFlow Lite

Pixel Visual Core (PVC)

TensorFlow 2.0

Features

AutoDifferentiation

Eager execution

Distribute

Losses

Metrics

TF.nn

Optimizers

Usage and extensions

TensorFlow

TensorFlow.js

TFLite

TFX

Integrations

Numpy

Extensions

Google Colab

Google JAX

Applications

Medical

Social media

Search Engine

Education

Retail

Research

See also

Bibliography

External links

References