Keraflow
Deep Learning for Python.
 All Classes Namespaces Functions Pages
keraflow.callbacks.ModelCheckpoint Class Reference

Save the model after every epoch. More...

Inheritance diagram for keraflow.callbacks.ModelCheckpoint:
keraflow.callbacks.Callback

Public Member Functions

def __init__
 

Detailed Description

Save the model after every epoch.

Constructor & Destructor Documentation

def keraflow.callbacks.ModelCheckpoint.__init__ (   self,
  filepath,
  monitor = 'val_loss',
  verbose = 0,
  save_on_improvement = False,
  mode = 'auto' 
)
Parameters
filepathstr. Path to save the model weights.
monitorstr. Quantity to monitor.
verboseverbosity mode, 0 or 1.
save_on_improvementboolean. If true, only saves the model when monitored quantity improves.
modeone of {auto, min, max}. Used only if save_on_improvement is true. Decides if the monitored quantity improves. If set to max, increase of the quantity indicates improvement, and vice versa. If set to 'auto', behaves like 'max' if monitor contains substring 'acc'. Otherwise, behaves like 'min'.