Search⌘ K

Evaluation

Understand how to evaluate deep learning models by measuring accuracy on test datasets using TensorFlow. Learn best practices for splitting datasets into training, validation, and test sets to assess model performance effectively.

Chapter Goals:

  • Evaluate model performance on a test set

A. Evaluating using accuracy

After training a model, it is a good idea to evaluate its performance. We do this by using a test set (i.e. data points not used in model training) and observe the model's prediction accuracy on the test set.

The code for this chapter makes use of the accuracy metric defined in ...