TensorFlow

Last updated

TensorFlow
Developer(s) Google Brain Team [1]
Initial releaseNovember 9, 2015;9 years ago (2015-11-09)
Repository github.com/tensorflow/tensorflow
Written in Python, C++, CUDA
Platform Linux, macOS, Windows, Android, JavaScript [2]
Type Machine learning library
License Apache 2.0
Website tensorflow.org

TensorFlow is a software library for machine learning and artificial intelligence. It can be used across a range of tasks, but is used mainly for training and inference of neural networks. [3] [4] It is one of the most popular deep learning frameworks, alongside others such as PyTorch and PaddlePaddle. [5] [6] It is free and open-source software released under the Apache License 2.0.

Contents

It was developed by the Google Brain team for Google's internal use in research and production. [7] [8] [9] The initial version was released under the Apache License 2.0 in 2015. [1] [10] Google released an updated version, TensorFlow 2.0, in September 2019. [11]

TensorFlow can be used in a wide variety of programming languages, including Python, JavaScript, C++, and Java, [12] facilitating its use in a range of applications in many sectors.

History

DistBelief

Starting in 2011, Google Brain built DistBelief as a proprietary machine learning system based on deep learning neural networks. Its use grew rapidly across diverse Alphabet companies in both research and commercial applications. [13] [14] Google assigned multiple computer scientists, including Jeff Dean, to simplify and refactor the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow. [15] In 2009, the team, led by Geoffrey Hinton, had implemented generalized backpropagation and other improvements, which allowed generation of neural networks with substantially higher accuracy, for instance a 25% reduction in errors in speech recognition. [16]

TensorFlow

TensorFlow is Google Brain's second-generation system. Version 1.0.0 was released on February 11, 2017. [17] While the reference implementation runs on single devices, TensorFlow can run on multiple CPUs and GPUs (with optional CUDA and SYCL extensions for general-purpose computing on graphics processing units). [18] TensorFlow is available on 64-bit Linux, macOS, Windows, and mobile computing platforms including Android and iOS.[ citation needed ]

Its flexible architecture allows for 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 graphs. The name TensorFlow derives from the operations that such neural networks perform on multidimensional data arrays, which are referred to as tensors . [19] During the Google I/O Conference in June 2016, Jeff Dean stated that 1,500 repositories on GitHub mentioned TensorFlow, of which only 5 were from Google. [20]

In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in JavaScript. [21]

In Jan 2019, Google announced TensorFlow 2.0. [22] It became officially available in September 2019. [11]

In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics. [23]

Tensor processing unit (TPU)

In May 2016, Google announced its Tensor processing unit (TPU), an application-specific integrated circuit (ASIC, a hardware chip) built specifically for machine learning and tailored for TensorFlow. A TPU is a programmable AI accelerator designed to provide high throughput of low-precision arithmetic (e.g., 8-bit), and oriented toward using or running models rather than training 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 better-optimized performance per watt for machine learning. [24]

In May 2017, Google announced the second-generation, as well as the availability of the TPUs in Google Compute Engine. [25] 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.[ citation needed ]

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. [26]

In February 2018, Google announced that they were making TPUs available in beta on the Google Cloud Platform. [27]

Edge TPU

In July 2018, the Edge TPU was announced. Edge TPU is Google's purpose-built ASIC chip designed to run TensorFlow Lite machine learning (ML) models on small client computing devices such as smartphones [28] known as edge computing.

TensorFlow Lite

In May 2017, Google announced a software stack specifically for mobile development, TensorFlow Lite. [29] In January 2019, the 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. [30] In May 2019, Google announced that their TensorFlow Lite Micro (also known as TensorFlow Lite for Microcontrollers) and ARM's uTensor would be merging. [31]

TensorFlow 2.0

As TensorFlow's market share among research papers was declining to the advantage of PyTorch, [32] 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 and later PyTorch. [32] 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. [33]

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 backpropagation which require gradients to optimize performance. [34] 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. [34]

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. [35] 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. [35] This execution paradigm is considered to be easier to debug because of its step by step transparency. [35]

Distribute

In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies. [36] This distributed computing can often speed up the execution of training and evaluating of TensorFlow models and is a common practice in the field of AI. [36] [37]

Losses

To train and assess models, TensorFlow provides a set of loss functions (also known as cost functions). [38] Some popular examples include mean squared error (MSE) and binary cross entropy (BCE). [38]

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). [39]

TF.nn

TensorFlow.nn is a module for executing primitive neural network operations on models. [40] Some of these operations include variations of convolutions (1/2/3D, Atrous, depthwise), activation functions (Softmax, RELU, GELU, Sigmoid, etc.) and their variations, and other operations (max-pooling, bias-add, etc.). [40]

Optimizers

TensorFlow offers a set of optimizers for training neural networks, including ADAM, ADAGRAD, and Stochastic Gradient Descent (SGD). [41] When training a model, different optimizers offer different modes of parameter tuning, often affecting a model's convergence and performance. [42]

Usage and extensions

TensorFlow

TensorFlow serves as a core platform and library for machine learning. TensorFlow's APIs use Keras to allow users to make their own machine-learning models. [33] [43] 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. [44]

TensorFlow provides a stable Python Application Program Interface (API), [45] as well as APIs without backwards compatibility guarantee for Javascript, [46] C++, [47] and Java. [48] [12] Third-party language binding packages are also available for C#, [49] [50] Haskell, [51] Julia, [52] MATLAB, [53] Object Pascal, [54] R, [55] Scala, [56] Rust, [57] OCaml, [58] and Crystal. [59] Bindings that are now archived and unsupported include Go [60] and Swift. [61]

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. [44] [62]

TFLite

TensorFlow Lite has APIs for mobile apps or embedded devices to generate and deploy TensorFlow models. [63] These models are compressed and optimized in order to be more efficient and have a higher performance on smaller capacity devices. [64]

TensorFlow Lite uses FlatBuffers as the data serialization format for network models, eschewing the Protocol Buffers format used by standard TensorFlow models. [64]

TFX

TensorFlow Extended (abbrev. TFX) provides numerous components to perform all the operations needed for end-to-end production. [65] Components include loading, validating, and transforming data, tuning, training, and evaluating the machine learning model, and pushing the model itself into production. [44] [65]

Integrations

Numpy

Numpy is one of the most popular Python data libraries, and TensorFlow offers integration and compatibility with its data structures. [66] Numpy NDarrays, the library's native datatype, are automatically converted to TensorFlow Tensors in TF operations; the same is also true vice versa. [66] 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. [66]

Extensions

TensorFlow also offers a variety of libraries and extensions to advance and extend the models and methods used. [67] 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. [68] Other add-ons, libraries, and frameworks include TensorFlow Model Optimization, TensorFlow Probability, TensorFlow Quantum, and TensorFlow Decision Forests. [67] [68]

Google Colab

Google also released Colaboratory, a TensorFlow Jupyter notebook environment that does not require any setup. [69] It runs on Google Cloud and allows users free access to GPUs and the ability to store and share notebooks on Google Drive. [70]

Google JAX

Google JAX is a machine learning framework for transforming numerical functions. [71] [72] [73] It is described as bringing together a modified version of autograd (automatic obtaining of the gradient function through differentiation of a function) and TensorFlow's 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 PyTorch. The primary functions of JAX are: [71]

  1. grad: automatic differentiation
  2. jit: compilation
  3. vmap: auto-vectorization
  4. pmap: SPMD programming

Applications

Medical

GE Healthcare used TensorFlow to increase the speed and accuracy of MRIs in identifying specific body parts. [74] Google used TensorFlow to create DermAssist, a free mobile application that allows users to take pictures of their skin and identify potential health complications. [75] Sinovation Ventures used TensorFlow to identify and classify eye diseases from optical coherence tomography (OCT) scans. [75]

Social media

Twitter implemented TensorFlow to rank tweets by importance for a given user, and changed their platform to show tweets in order of this ranking. [76] Previously, tweets were simply shown in reverse chronological order. [76] The photo sharing app VSCO used TensorFlow to help suggest custom filters for photos. [75]

Search Engine

Google officially released RankBrain on October 26, 2015, backed by TensorFlow. [77]

Education

InSpace, a virtual learning platform, used TensorFlow to filter out toxic chat messages in classrooms. [78] Liulishuo, an online English learning platform, utilized TensorFlow to create an adaptive curriculum for each student. [79] 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. [79]

Retail

The e-commerce platform Carousell used TensorFlow to provide personalized recommendations for customers. [75] The cosmetics company ModiFace used TensorFlow to create an augmented reality experience for customers to test various shades of make-up on their face. [80]

TorontoMusicGarden10.jpg
TorontoMusicGarden10-TensorFlow2.jpg
2016 comparison of original photo (left) and with TensorFlow neural style applied (right)

Research

TensorFlow is the foundation for the automated image-captioning software DeepDream. [81]

See also

Related Research Articles

This is a comparison of web frameworks for front-end web development that are heavily reliant on JavaScript code for their behavior.

<span class="mw-page-title-main">Etherpad</span> Open-source web-based collaborative real-time editor

Etherpad is an open-source, web-based collaborative real-time editor, allowing authors to simultaneously edit a text document, and see all of the participants' edits in real-time, with the ability to display each author's text in their own color. There is also a chat box in the sidebar to allow meta communication.

<span class="mw-page-title-main">Node.js</span> JavaScript runtime environment

Node.js is a cross-platform, open-source JavaScript runtime environment that can run on Windows, Linux, Unix, macOS, and more. Node.js runs on the V8 JavaScript engine, and executes JavaScript code outside a web browser.

<span class="mw-page-title-main">Ember.js</span> JavaScript framework

Ember.js is an open-source JavaScript web framework that utilizes a component-service pattern. It is designed to allow developers to create scalable single-page web applications by incorporating common idioms, best practices, and patterns from other single-page-app ecosystem patterns into the framework.

Google Cloud Platform (GCP) is a suite of cloud computing services offered by Google that provides a series of modular cloud services including computing, data storage, data analytics, and machine learning, alongside a set of management tools. It runs on the same infrastructure that Google uses internally for its end-user products, such as Google Search, Gmail, and Google Docs, according to Verma et al. Registration requires a credit card or bank account details.

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.

<span class="mw-page-title-main">WebAssembly</span> Cross-platform assembly language and bytecode designed for execution in web browsers

WebAssembly (Wasm) defines a portable binary-code format and a corresponding text format for executable programs as well as software interfaces for facilitating communication between such programs and their host environment.

The following tables compare notable software frameworks, libraries, and computer programs for deep learning applications.

<span class="mw-page-title-main">Tensor Processing Unit</span> AI accelerator ASIC by Google

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.

<span class="mw-page-title-main">Keras</span> Neural network library

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." Keras 3 will be the default Keras version for TensorFlow 2.16 onwards, but Keras 2 can still be used.

Google AI is a division of Google dedicated to artificial intelligence. It was announced at Google I/O 2017 by CEO Sundar Pichai.

<span class="mw-page-title-main">ML.NET</span> Machine learning library

ML.NET is a free software machine learning library for the C# and F# programming languages. It also supports Python models when used together with NimbusML. The preview release of ML.NET included transforms for feature engineering like n-gram creation, and learners to handle binary classification, multi-class classification, and regression tasks. Additional ML tasks like anomaly detection and recommendation systems have since been added, and other approaches like deep learning will be included in future versions.

The bfloat16 floating-point format is a computer number format occupying 16 bits in computer memory; it represents a wide dynamic range of numeric values by using a floating radix point. This format is a shortened (16-bit) version of the 32-bit IEEE 754 single-precision floating-point format (binary32) with the intent of accelerating machine learning and near-sensor computing. It preserves the approximate dynamic range of 32-bit floating-point numbers by retaining 8 exponent bits, but supports only an 8-bit precision rather than the 24-bit significand of the binary32 format. More so than single-precision 32-bit floating-point numbers, bfloat16 numbers are unsuitable for integer calculations, but this is not their intended use. Bfloat16 is used to reduce the storage requirements and increase the calculation speed of machine learning algorithms.

<span class="mw-page-title-main">Flux (machine-learning framework)</span> Open-source machine-learning software library

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.

Amazon SageMaker AI is a cloud-based machine-learning platform that allows the creation, training, and deployment by developers of machine-learning (ML) models on the cloud. It can be used to deploy ML models on embedded systems and edge-devices. The platform was launched in November 2017.

Kubeflow is an open-source platform for machine learning and MLOps on Kubernetes introduced by Google. The different stages in a typical machine learning lifecycle are represented with different software components in Kubeflow, including model development (Kubeflow Notebooks), model training (Kubeflow Pipelines,Kubeflow Training Operator), model serving (KServe), and automated machine learning (Katib).

OpenVINO is an open-source software toolkit for optimizing and deploying deep learning models. It enables programmers to develop scalable and efficient AI solutions with relatively few lines of code. It supports several popular model formats and categories, such as large language models, computer vision, and generative AI.

The Fashion MNIST dataset is a large freely available database of fashion images that is commonly used for training and testing various machine learning systems. Fashion-MNIST was intended to serve as a replacement for the original MNIST database for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits.

Hugging Face, Inc. is an American company incorporated under the Delaware General Corporation Law and based in New York City that develops computation tools for building applications using machine learning. It is most notable for its transformers library built for natural language processing applications and its platform that allows users to share machine learning models and datasets and showcase their work.

MobileNet is a family of convolutional neural network (CNN) architectures designed for image classification, object detection, and other computer vision tasks. They are designed for small size, low latency, and low power consumption, making them suitable for on-device inference and edge computing on resource-constrained devices like mobile phones and embedded systems. They were originally designed to be run efficiently on mobile devices with TensorFlow Lite.

References

  1. 1 2 "Credits". TensorFlow.org. Archived from the original on November 17, 2015. Retrieved November 10, 2015.
  2. ↑ "TensorFlow.js". Archived from the original on May 6, 2018. Retrieved June 28, 2018.
  3. ↑ Abadi, Martín; Barham, Paul; Chen, Jianmin; Chen, Zhifeng; Davis, Andy; Dean, Jeffrey; Devin, Matthieu; Ghemawat, Sanjay; Irving, Geoffrey; Isard, Michael; Kudlur, Manjunath; Levenberg, Josh; Monga, Rajat; Moore, Sherry; Murray, Derek G.; Steiner, Benoit; Tucker, Paul; Vasudevan, Vijay; Warden, Pete; Wicke, Martin; Yu, Yuan; Zheng, Xiaoqiang (2016). TensorFlow: A System for Large-Scale Machine Learning (PDF). Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). arXiv: 1605.08695 . Archived (PDF) from the original on December 12, 2020. Retrieved October 26, 2020.
  4. ↑ TensorFlow: Open source machine learning. Google. 2015. Archived from the original on November 11, 2021. "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
  5. ↑ "Top 30 Open Source Projects". Open Source Project Velocity by CNCF. Retrieved October 12, 2023.
  6. ↑ "Welcome to the PaddlePaddle GitHub". PaddlePaddle Official Github Repo. Retrieved October 28, 2024.
  7. ↑ Video clip by Google about TensorFlow 2015 at minute 0:15/2:17
  8. ↑ Video clip by Google about TensorFlow 2015 at minute 0:26/2:17
  9. ↑ Dean et al 2015 , p. 2
  10. ↑ Metz, Cade (November 9, 2015). "Google Just Open Sourced TensorFlow, Its Artificial Intelligence Engine". Wired . Archived from the original on November 9, 2015. Retrieved November 10, 2015.
  11. 1 2 TensorFlow (September 30, 2019). "TensorFlow 2.0 is now available!". Medium. Archived from the original on October 7, 2019. Retrieved November 24, 2019.
  12. 1 2 "API Documentation". Archived from the original on November 16, 2015. Retrieved June 27, 2018.,
  13. ↑ Dean, Jeff; Monga, Rajat; et al. (November 9, 2015). "TensorFlow: Large-scale machine learning on heterogeneous systems" (PDF). TensorFlow.org. Google Research. Archived (PDF) from the original on November 20, 2015. Retrieved November 10, 2015.
  14. ↑ Perez, Sarah (November 9, 2015). "Google Open-Sources The Machine Learning Tech Behind Google Photos Search, Smart Reply And More". TechCrunch. Archived from the original on November 9, 2015. Retrieved November 11, 2015.
  15. ↑ Oremus, Will (November 9, 2015). "What Is TensorFlow, and Why Is Google So Excited About It?". Slate. Archived from the original on November 10, 2015. Retrieved November 11, 2015.
  16. ↑ Ward-Bailey, Jeff (November 25, 2015). "Google chairman: We're making 'real progress' on artificial intelligence". CSMonitor. Archived from the original on September 16, 2015. Retrieved November 25, 2015.
  17. ↑ TensorFlow Developers (2022). "Tensorflow Release 1.0.0". GitHub . doi:10.5281/zenodo.4724125. Archived from the original on February 27, 2021. Retrieved July 24, 2017.
  18. ↑ Metz, Cade (November 10, 2015). "TensorFlow, Google's Open Source AI, Points to a Fast-Changing Hardware World". Wired. Archived from the original on November 11, 2015. Retrieved November 11, 2015.
  19. ↑ "Introduction to tensors". tensorflow.org. Archived from the original on May 26, 2024. Retrieved March 3, 2024.
  20. ↑ Machine Learning: Google I/O 2016 Minute 07:30/44:44 . Archived December 21, 2016, at the Wayback Machine . Retrieved 5 June 2016.
  21. ↑ TensorFlow (March 30, 2018). "Introducing TensorFlow.js: Machine Learning in Javascript". Medium. Archived from the original on March 30, 2018. Retrieved May 24, 2019.
  22. ↑ TensorFlow (January 14, 2019). "What's coming in TensorFlow 2.0". Medium. Archived from the original on January 14, 2019. Retrieved May 24, 2019.
  23. ↑ TensorFlow (May 9, 2019). "Introducing TensorFlow Graphics: Computer Graphics Meets Deep Learning". Medium. Archived from the original on May 9, 2019. Retrieved May 24, 2019.
  24. ↑ Jouppi, Norm. "Google supercharges machine learning tasks with TPU custom chip". Google Cloud Platform Blog. Archived from the original on May 18, 2016. Retrieved May 19, 2016.
  25. ↑ "Build and train machine learning models on our new Google Cloud TPUs". Google. May 17, 2017. Archived from the original on May 17, 2017. Retrieved May 18, 2017.
  26. ↑ "Cloud TPU". Google Cloud. Archived from the original on May 17, 2017. Retrieved May 24, 2019.
  27. ↑ "Cloud TPU machine learning accelerators now available in beta". Google Cloud Platform Blog. Archived from the original on February 12, 2018. Retrieved February 12, 2018.
  28. ↑ Kundu, Kishalaya (July 26, 2018). "Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018". Beebom. Archived from the original on May 26, 2024. Retrieved February 2, 2019.
  29. ↑ "Google's new machine learning framework is going to put more AI on your phone". May 17, 2017. Archived from the original on May 17, 2017. Retrieved May 19, 2017.
  30. ↑ TensorFlow (January 16, 2019). "TensorFlow Lite Now Faster with Mobile GPUs (Developer Preview)". Medium. Archived from the original on January 16, 2019. Retrieved May 24, 2019.
  31. ↑ "uTensor and Tensor Flow Announcement | Mbed". os.mbed.com. Archived from the original on May 9, 2019. Retrieved May 24, 2019.
  32. 1 2 He, Horace (October 10, 2019). "The State of Machine Learning Frameworks in 2019". The Gradient. Archived from the original on October 10, 2019. Retrieved May 22, 2020.
  33. 1 2 Ciaramella, Alberto; Ciaramella, Marco (July 2024). Introduction to Artificial Intelligence: from data analysis to generative AI. Intellisemantic Editions. ISBN   9788894787603.
  34. 1 2 "Introduction to gradients and automatic differentiation". TensorFlow. Archived from the original on October 28, 2021. Retrieved November 4, 2021.
  35. 1 2 3 "Eager execution | TensorFlow Core". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  36. 1 2 "Module: tf.distribute | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on May 26, 2024. Retrieved November 4, 2021.
  37. ↑ Sigeru., Omatu (2014). Distributed Computing and Artificial Intelligence, 11th International Conference. Springer International Publishing. ISBN   978-3-319-07593-8. OCLC   980886715. Archived from the original on May 26, 2024. Retrieved November 4, 2021.
  38. 1 2 "Module: tf.losses | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on October 27, 2021. Retrieved November 4, 2021.
  39. ↑ "Module: tf.metrics | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  40. 1 2 "Module: tf.nn | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on May 26, 2024. Retrieved November 6, 2021.
  41. ↑ "Module: tf.optimizers | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on October 30, 2021. Retrieved November 6, 2021.
  42. ↑ Dogo, E. M.; Afolabi, O. J.; Nwulu, N. I.; Twala, B.; Aigbavboa, C. O. (December 2018). "A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks". 2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS). pp. 92–99. doi:10.1109/CTEMS.2018.8769211. ISBN   978-1-5386-7709-4. S2CID   198931032. Archived from the original on May 26, 2024. Retrieved July 25, 2023.
  43. ↑ "TensorFlow Core | Machine Learning for Beginners and Experts". TensorFlow. Archived from the original on January 20, 2023. Retrieved November 4, 2021.
  44. 1 2 3 "Introduction to TensorFlow". TensorFlow. Archived from the original on January 20, 2023. Retrieved October 28, 2021.
  45. ↑ "All symbols in TensorFlow 2 | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021.
  46. ↑ "TensorFlow.js". js.tensorflow.org. Archived from the original on May 26, 2024. Retrieved November 6, 2021.
  47. ↑ "TensorFlow C++ API Reference | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on January 20, 2023. Retrieved November 6, 2021.
  48. ↑ "org.tensorflow | Java". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021.
  49. ↑ Icaza, Miguel de (February 17, 2018). "TensorFlowSharp: TensorFlow API for .NET languages". GitHub . Archived from the original on July 24, 2017. Retrieved February 18, 2018.
  50. ↑ Chen, Haiping (December 11, 2018). "TensorFlow.NET: .NET Standard bindings for TensorFlow". GitHub . Archived from the original on July 12, 2019. Retrieved December 11, 2018.
  51. ↑ "haskell: Haskell bindings for TensorFlow". tensorflow. February 17, 2018. Archived from the original on July 24, 2017. Retrieved February 18, 2018.
  52. ↑ Malmaud, Jon (August 12, 2019). "A Julia wrapper for TensorFlow". GitHub . Archived from the original on July 24, 2017. Retrieved August 14, 2019. operations like sin, * (matrix multiplication), .* (element-wise multiplication), etc [..]. Compare to Python, which requires learning specialized namespaced functions like tf.matmul.
  53. ↑ "A MATLAB wrapper for TensorFlow Core". GitHub . November 3, 2019. Archived from the original on September 14, 2020. Retrieved February 13, 2020.
  54. ↑ "Use TensorFlow from Pascal (FreePascal, Lazarus, etc.)". GitHub . January 19, 2023. Archived from the original on January 20, 2023. Retrieved January 20, 2023.
  55. ↑ "tensorflow: TensorFlow for R". RStudio. February 17, 2018. Archived from the original on January 4, 2017. Retrieved February 18, 2018.
  56. ↑ Platanios, Anthony (February 17, 2018). "tensorflow_scala: TensorFlow API for the Scala Programming Language". GitHub . Archived from the original on February 18, 2019. Retrieved February 18, 2018.
  57. ↑ "rust: Rust language bindings for TensorFlow". tensorflow. February 17, 2018. Archived from the original on July 24, 2017. Retrieved February 18, 2018.
  58. ↑ Mazare, Laurent (February 16, 2018). "tensorflow-ocaml: OCaml bindings for TensorFlow". GitHub . Archived from the original on June 11, 2018. Retrieved February 18, 2018.
  59. ↑ "fazibear/tensorflow.cr". GitHub. Archived from the original on June 27, 2018. Retrieved October 10, 2018.
  60. ↑ "tensorflow package - github.com/tensorflow/tensorflow/tensorflow/go - pkg.go.dev". pkg.go.dev. Archived from the original on November 6, 2021. Retrieved November 6, 2021.
  61. ↑ "Swift for TensorFlow (In Archive Mode)". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021.
  62. ↑ "TensorFlow.js | Machine Learning for JavaScript Developers". TensorFlow. Archived from the original on November 4, 2021. Retrieved October 28, 2021.
  63. ↑ "TensorFlow Lite | ML for Mobile and Edge Devices". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 1, 2021.
  64. 1 2 "TensorFlow Lite". TensorFlow. Archived from the original on November 2, 2021. Retrieved November 1, 2021.
  65. 1 2 "TensorFlow Extended (TFX) | ML Production Pipelines". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 2, 2021.
  66. 1 2 3 "Customization basics: tensors and operations | TensorFlow Core". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021.
  67. 1 2 "Guide | TensorFlow Core". TensorFlow. Archived from the original on July 17, 2019. Retrieved November 4, 2021.
  68. 1 2 "Libraries & extensions". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  69. ↑ "Colaboratory – Google". research.google.com. Archived from the original on October 24, 2017. Retrieved November 10, 2018.
  70. ↑ "Google Colaboratory". colab.research.google.com. Archived from the original on February 3, 2021. Retrieved November 6, 2021.
  71. 1 2 Bradbury, James; Frostig, Roy; Hawkins, Peter; Johnson, Matthew James; Leary, Chris; MacLaurin, Dougal; Necula, George; Paszke, Adam; Vanderplas, Jake; Wanderman-Milne, Skye; Zhang, Qiao (June 18, 2022), "JAX: Autograd and XLA", Astrophysics Source Code Library, Google, Bibcode:2021ascl.soft11002B, archived from the original on June 18, 2022, retrieved June 18, 2022
  72. ↑ "Using JAX to accelerate our research". www.deepmind.com. Archived from the original on June 18, 2022. Retrieved June 18, 2022.
  73. ↑ "Why is Google's JAX so popular?". Analytics India Magazine. April 25, 2022. Archived from the original on June 18, 2022. Retrieved June 18, 2022.
  74. ↑ "Intelligent Scanning Using Deep Learning for MRI". Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  75. 1 2 3 4 "Case Studies and Mentions". TensorFlow. Archived from the original on October 26, 2021. Retrieved November 4, 2021.
  76. 1 2 "Ranking Tweets with TensorFlow". Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  77. ↑ Davies, Dave (September 2, 2020). "A Complete Guide to the Google RankBrain Algorithm". Search Engine Journal. Archived from the original on November 6, 2021. Retrieved October 15, 2024.
  78. ↑ "InSpace: A new video conferencing platform that uses TensorFlow.js for toxicity filters in chat". Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  79. 1 2 Xulin. "流利说基于 TensorFlow 的自适应系统实践". Weixin Official Accounts Platform. Archived from the original on November 6, 2021. Retrieved November 4, 2021.
  80. ↑ "How Modiface utilized TensorFlow.js in production for AR makeup try on in the browser". Archived from the original on November 4, 2021. Retrieved November 4, 2021.
  81. ↑ Byrne, Michael (November 11, 2015). "Google Offers Up Its Entire Machine Learning Library as Open-Source Software". Vice. Archived from the original on January 25, 2021. Retrieved November 11, 2015.

Further reading

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.