|
Keraflow
Deep Learning for Python.
|
Stop training when a monitored quantity has stopped improving. More...
Public Member Functions | |
| def | __init__ |
Stop training when a monitored quantity has stopped improving.
| def keraflow.callbacks.EarlyStopping.__init__ | ( | self, | |
monitor = 'val_loss', |
|||
patience = 0, |
|||
verbose = 0, |
|||
mode = 'auto' |
|||
| ) |
| monitor | str. Quantity to monitor. |
| patience | number of epochs with no improvement after which training will be stopped. |
| verbose | verbosity mode, 0 or 1. |
| mode | one of {auto, min, max}. 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'. |