Keras Callbacks

from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
from keras.callbacks import ReduceLROnPlateau

checkpoint = ModelCheckpoint("D:/development/DeepLearningCV/Trained Models/MNIST_Checkpoint.h5",
                             monitor="val_loss",
                             mode="min",
                             save_best_only = True,
                             verbose=1)

earlystop = EarlyStopping(monitor = 'val_loss', # value being monitored for improvement
                          min_delta = 0, #Abs value and is the min change required before we stop
                          patience = 3, #Number of epochs we wait before stopping 
                          verbose = 1,
                          restore_best_weights = True) #keeps the best weigths once stopped

reduce_lr = ReduceLROnPlateau(monitor = 'val_loss', factor = 0.2, patience = 3, verbose = 1, min_delta = 0.0001)

#If no improvement is seen in our monitored metric (val_loss typically), we wait a certain number of epochs (patience) then this callback reduces the learning rate by a factor

callbacks = [earlystop, checkpoint, reduce_lr ]

history = model.fit(x_train, y_train,
          batch_size=64,
          epochs=3,
          verbose=2,
          callbacks = callbacks,
          validation_data=(x_test, y_test))


score = model.evaluate(x_test, y_test, verbose=0)