start

If you’re not familiar with machine learning, we recommend you take the following online course before delving into the TensorFlow documentation:

  • Crash Course in Machine Learning: Introduces machine learning concepts and encourages experimentation with existing TensorFlow code.

TensorFlow is a machine learning tool designed primarily for deep neural network models, as well as a number of other features.

The easiest way to get started with TensorFlow is to use Eager Execution.

Start using Eager Execution

TensorFlow provides a number of apis. The rest of this section focuses on the Estimator API that provides an extensible high-performance model. To get started with Estimators, read the following documentation:

  • Introduction to Graph Execution
  • Premade Estimators

The following documentation describes key features in the higher-level API:

  • checkpoint
  • Characteristics of the column
  • Data sets: A quick look
  • Create a custom Estimator

The following documentation is for advanced users:

  • Introduction to underlying API programming
  • Developer guide
  • The tutorial