Deep Learning Quick Reference

Training

Now that we've defined our neural network and loaded our data, all that's left is to train it.

In this, and several other examples throughout the book I'm using a dictionary called data to pass around the various datasets such as train_X, val_X, and test_X. I use this notation to keep the code readable, and because passing the entire dictionary is necessary more often than not.

Here's how I will train the model we've just built.

model = build_network(data["train_X"].shape[1])model.fit(x=data["train_X"], y=data["train_y"],          batch_size=30,          epochs=50,          validation_data=(data["val_X"], data["val_y"]),          verbose=1,          callbacks=callbacks)

I'm using the same callbacks that we've previously used. I'm not using the ROC AUC callback we built in ...