Keraflow
Deep Learning for Python.
|
Save the model after every epoch. More...
Public Member Functions | |
def | __init__ |
Save the model after every epoch.
def keraflow.callbacks.ModelCheckpoint.__init__ | ( | self, | |
filepath, | |||
monitor = 'val_loss' , |
|||
verbose = 0 , |
|||
save_on_improvement = False , |
|||
mode = 'auto' |
|||
) |
filepath | str. Path to save the model weights. |
monitor | str. Quantity to monitor. |
verbose | verbosity mode, 0 or 1. |
save_on_improvement | boolean. If true, only saves the model when monitored quantity improves. |
mode | one 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'. |