Early stopping: Optimizing the optimization

Now that you know how to monitor your model performance throughout optimization, you can use early stopping to stop optimization when it isn't helping any more. Since the optimization stops automatically when it isn't helping, you can also set a high value for epochs in your call to .fit(), as Dan showed in the video.

The model you'll optimize has been specified as model. As before, the data is pre-loaded as predictors and target.

This exercise is part of the course

Introduction to Deep Learning in Python

View Course

Exercise instructions

Import EarlyStopping from tensorflow.keras.callbacks.
Compile the model, once again using 'adam' as the optimizer, 'categorical_crossentropy' as the loss function, and metrics=['accuracy'] to see the accuracy at each epoch.
Create an EarlyStopping object called early_stopping_monitor. Stop optimization when the validation loss hasn't improved for 2 epochs by specifying the patience parameter of EarlyStopping() to be 2.
Fit the model using the predictors and target. Specify the number of epochs to be 30 and use a validation split of 0.3. In addition, pass [early_stopping_monitor] to the callbacks parameter.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Import EarlyStopping
____

# Save the number of columns in predictors: n_cols
n_cols = predictors.shape[1]
input_shape = (n_cols,)

# Specify the model
model = Sequential()
model.add(Dense(100, activation='relu', input_shape = input_shape))
model.add(Dense(100, activation='relu'))
model.add(Dense(2, activation='softmax'))

# Compile the model
____

# Define early_stopping_monitor
early_stopping_monitor = ____

# Fit the model
____

Edit and Run Code