Evaluating models

We have already learned how to train a regression and classification algorithm in TensorFlow. After this, we must be able to evaluate the model's predictions to determine how well it did.

Getting ready

Evaluating models is very important and every subsequent model will have some form of model evaluation. Using TensorFlow, we must build this feature into the computational graph and call it while our model is training and/or after it has finished training.

Evaluating models during training gives us an insight into the algorithm and may give us hints to debug it, improve it, or change models entirely. While evaluation during training isn't always necessary, we will show how to do it with both regression and classification.

After training, we need to quantify how the model performs on the data. Ideally, we have a separate training and test set (and even a validation set) on which we can evaluate the model.

When we want to evaluate a model, we will want to do so on a large batch...