Custom training: basics

In the previous tutorial we covered the TensorFlow APIs for automatic differentiation, a basic building block for machine learning. In this tutorial we will use the TensorFlow primitives introduced in the prior tutorials to do some simple machine learning. TensorFlow also includes a higher-level neural networks API (tf.keras) which provides useful abstractions to reduce boilerplate.

Automatic differentiation and gradient tape

In the previous tutorial we introduced Tensors and operations on them. In this tutorial we will cover automatic differentiation, a key technique for optimizing machine learning models. Setup import tensorflow as tf tf.enable_eager_execution() tfe = tf.contrib.eager # Shorthand for some symbols Derivatives of a function TensorFlow provides APIs for automatic differentiation – computing the derivative

Lesson 6: Eager execution basics – Keras

This is an introductory tutorial for using TensorFlow. It will cover: Importing required packages Creating and using Tensors Using GPU acceleration Datasets Import TensorFlow To get started, import the tensorflow module and enable eager execution. Eager execution enables a more interactive frontend to TensorFlow, the details of which we will discuss much later. import tensorflow

Lesson 5: Save and restore models

Model progress can be saved during—and after—training. This means a model can resume where it left off and avoid long training times. Saving also means you can share your model and others can recreate your work. When publishing research models and techniques, most machine learning practitioners share: code to create the model, and the trained

Lesson 2: Text classification with Keras

After learning about basic classification at lesson 1: Basic classification. Today, we learn about text classification with Keras. This notebook classifies movie reviews as positive or negative using the text of the review. This is an example of binary—or two-class—classification, an important and widely applicable kind of machine learning problem. We’ll use the IMDB dataset