Guides

TensorFlow 2 is an end-to-end, open-source machine learning platform. You can think of it as an infrastructure layer for differentiable programming. It combines four key abilities:

Efficiently executing low-level tensor operations on CPU, GPU, or TPU.
Computing the gradient of arbitrary differentiable expressions.
Scaling computation to many devices, such as clusters of hundreds of GPUs.
Exporting programs (“graphs”) to external runtimes such as servers, browsers, mobile and embedded devices.

TensorFlow 2 focuses on simplicity and ease of use, with features like eager execution, intuitive higher-level APIs, and flexible model building on any platform.

TensorFlow

Tensorflow Basics

Start here for a quick overview of TensorFlow basics.

Introduction to Tensors

Learn about Tensors, the multi-dimensional arrays used by TensorFlow.

Introduction to gradients and automatic differentiation

Learn how to compute gradients with automatic differentiation in TensorFlow, the capability that powers machine learning algorithms such as backpropagation.

Introduction to graphs and `tf_function()`

Go beneath the surface and learn about TensorFlow Graphs.

Tensor Slicing

Advanced guide for working with sub-sections (slices) of Tensors.

Keras

Keras is the high-level API of TensorFlow 2: an approachable, highly-productive interface for solving machine learning problems, with a focus on modern deep learning. It provides essential abstractions and building blocks for developing and shipping machine learning solutions with high iteration velocity.

Keras empowers engineers and researchers to take full advantage of the scalability and cross-platform capabilities of TensorFlow 2.

Making custom layer and model objects.

Complete guide to writing custom layer and model classes.

Serialization and saving

Complete guide to saving & serializing models.

Working with preprocessing layers

Overview of how to leverage preprocessing layers to create end-to-end models.

Customizing what happens in `fit()`

When you’re doing supervised learning, you can use fit() and everything works smoothly.

Writing a training loop from scratch

Complete guide to writing low-level training & evaluation loops.

Working with RNNs

Guide to using and customizing recurrent neural networks, a class of neural networks for modeling sequence data such as time series or natural language.

Understanding masking & padding

Complete guide to using mask-aware sequence layers in Keras.

Writing your own callbacks

Guide to writing Keras callbacks for customizing the behavior during model training, evaluation, or inference.

Transfer learning and fine-tuning

Guide to taking pre-trained models and adpating them to new, similar tasks.