Difficulty: beginner
Estimated Time: 10 minutes

This scenario is introduces the high level tf.contrib.learn API for the machine learning process. The training is performed on the MNIST dataset that is considered a Hello world for the deep learning examples. We will walk you through training process, evaluating the model and predicting new values using high level models called Estimators.

To take the most of this course you should know how to program in Python or other language that would allow you to understand Python syntax.

Congratulations!

You've completed TensorFlow Estimators for MNIST dataset scenario.

You've learned how to:

  • Read the MNIST dataset
  • Create the deep neural network classifier
  • Perform training and evaluate the model
  • Predict new values

Don’t stop now! The next scenario will only take about 10 minutes to complete.

TensorFlow Estimators for MNIST dataset

Step 1 of 4

Estimators

TensorFlow tf.contrib.learn is a high level API for machine learning process. It offers variety of Estimators that represent predefined models. Some of the examples are:

You are also provided with the techniques to write your own estimators if the list of available ones is not sufficient.

In this tutorial we will use the DNNClassifier to train the model and predict the labels for the MNIST dataset. We will be solving the classification task and try to recognise the actual digit from its handwritten representation.

MNIST Classification