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.
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!
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.
Google today introduced TensorFlow.Text, a library for preprocessing language models with TensorFlow. The open source machine learning framework created by the Google Brain team has seen more than 41 million downloads. TensorFlow.Text can be installed using PIP and comes with the ability to utilize tokens to break apart and analyze text like words, numbers, and punctuation. At launch, TensorFlow.Text can recognize white space, unicode script, and predetermined sequences of word fragments like suffixes or prefixes that Google calls wordpieces. Wordpieces are commonly used in approaches like BERT, a pretraining technique for language models Google open-sourced last fall.