TensorFlow Estimators are a high-level API for TensorFlow that allows you to create, train, and use deep learning models easily.

See the Quickstart tutorial for an introduction to the API.

To run most of these examples, you need to install the scikit learn library (pip install -U scikit-learn). Some examples use the pandas library for data processing (pip install -U pandas).

• Deep Neural Network Regression with Boston Data
• Deep Neural Network Classification with Iris Data
• Building a Custom Model
• Building a Model Using Different GPU Configurations

• Deep Neural Network with Customized Decay Function

• Building a Random Forest Model
• Building a Wide & Deep Model
• Building a Residual Network Model

• Text Classification Using Recurrent Neural Networks on Words
• Text Classification Using Convolutional Neural Networks on Words
• Text Classification Using Recurrent Neural Networks on Characters
• Text Classification Using Convolutional Neural Networks on Characters