Beginning Anomaly Detection Using

 Callbacks

 ModelCheckpoint

keras.callbacks.ModelCheckpoint()

ModelCheckpoint is basically a function that saves the model every epoch (unless 

otherwise directed via parameters). How it does so can be configured by the set of 

parameters associated with ModelCheckpoint():

• 

filepath: The path where you want to save the model file. Typing just 

“model_name.h5” saves it in the same directory.

• 

monitor: The quantity that you want the model to monitor. By 

default, it’s set to “val_loss”.

• 

verbose: Sets verbosity to 0 or 1. It’s set to 0 by default.

• 

save_best_only: If set to true, then the model with the best 

performance according to the quantity monitored will be saved.

•