Collaborating Authors



TensorFlow is an open source software library for numerical computation using data flow graphs. The graph nodes represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture enables you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device without rewriting code. TensorFlow also includes TensorBoard, a data visualization toolkit. TensorFlow was originally developed by researchers and engineers working on the Google Brain team within Google's Machine Intelligence Research organization for the purposes of conducting machine learning and deep neural networks research.

Tensors and operations TensorFlow.js


TensorFlow.js is a framework to define and run computations using tensors in JavaScript. A tensor is a generalization of vectors and matrices to higher dimensions. The central unit of data in TensorFlow.js is the tf.Tensor: a set of values shaped into an array of one or more dimensions. A tf.Tensor also contains the following properties: A tf.Tensor can be created from an array with the tf.tensor() method: TensorFlow.js also provides a set of convenience methods for creating random tensors, tensors filled with a particular value, tensors from HTMLImageElements, and many more which you can find here. The number of elements in a tf.Tensor is the product of the sizes in its shape.

Tutorials TensorFlow


This section contains tutorials demonstrating how to do specific tasks in TensorFlow. If you are new to TensorFlow, we recommend reading the documents in the "Get Started" section before reading these tutorials. These tutorials focus on machine learning problems dealing with sequence data. These tutorials demonstrate various data representations that can be used in TensorFlow. Although TensorFlow specializes in machine learning, the core of TensorFlow is a powerful numeric computation system which you can also use to solve other kinds of math problems.

Effective TensorFlow for Non-Experts – Frank's World


TensorFlow offers high level interfaces like Keras and Estimators, which can be used without being an AI or machine learning expert. Watch this talk to learn how to implement complex machine learning models and deploy them on any platform that supports TensorFlow.

TensorFlow at the O'Reilly AI Conference – TensorFlow – Medium


This fall, we've teamed up with Google Cloud and O'Reilly Media to present a full four days of TensorFlow training at the O'Reilly Artificial Intelligence conferences -- in both San Francisco (Sep 4–7) and London (Oct 8–11). We've worked with the conference organizer to make all of the tutorials and sessions open to any conference pass holder. We'll be presenting an entire track of TensorFlow-oriented sessions, delivered directly by members of the TensorFlow and Google Cloud ML teams. Attendance to the TensorFlow training and sessions is open to any conference attendee, from Pavilion Plus pass holders up: we look forward to meeting you and talking TensorFlow!