TensorFlow is an open source software library for numerical computation usingdata flow graphs. Nodes in the graph represent mathematical operations, whilethe graph edges represent the multidimensional data arrays (tensors) that flowbetween them. This flexible architecture lets you deploy computation to oneor more CPUs or GPUs in a desktop, server, or mobile device without rewritingcode. TensorFlow also includes TensorBoard, a data visualization toolkit.
TensorFlow was originally developed by researchers and engineersworking on the Google Brain team within Google's Machine Intelligence researchorganization for the purposes of conducting machine learning and deep neuralnetworks research. The system is general enough to be applicable in a widevariety of other domains, as well.
If you'd like to contribute to TensorFlow, be sure to review the contributionguidelines.
See Installing TensorFlow for instructions on how to install our release binaries or how to build from source.
People who are a little more adventurous can also try our nightly binaries:
import tensorflow as tf hello = tf.constant('Hello, TensorFlow!') sess = tf.Session() sess.run(hello) 'Hello, TensorFlow!' a = tf.constant(10) b = tf.constant(32) sess.run(a+b) 42
The TensorFlow community has created amazing things with TensorFlow, please see the resources section of tensorflow.org for an incomplete list.
git clone tensorflow-tensorflow_-_2017-06-09_22-35-42.bundle -b master