contrib.keras.callbacks.ReduceLROnPlateau

tf.contrib.keras.callbacks.ReduceLROnPlateau

class tf.contrib.keras.callbacks.ReduceLROnPlateau

Defined in tensorflow/contrib/keras/python/keras/callbacks.py.

Reduce learning rate when a metric has stopped improving.

Models often benefit from reducing the learning rate by a factor of 2-10 once learning stagnates. This callback monitors a quantity and if no improvement is seen for a 'patience' number of epochs, the learning rate is reduced.

Example: python reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.001) model.fit(X_train, Y_train, callbacks=[reduce_lr])

Arguments:

monitor: quantity to be monitored.
factor: factor by which the learning rate will
    be reduced. new_lr = lr * factor
patience: number of epochs with no improvement
    after which learning rate will be reduced.
verbose: int. 0: quiet, 1: update messages.
mode: one of {auto, min, max}. In `min` mode,
    lr will be reduced when the quantity
    monitored has stopped decreasing; in `max`
    mode it will be reduced when the quantity
    monitored has stopped increasing; in `auto`
    mode, the direction is automatically inferred
    from the name of the monitored quantity.
epsilon: threshold for measuring the new optimum,
    to only focus on significant changes.
cooldown: number of epochs to wait before resuming
    normal operation after lr has been reduced.
min_lr: lower bound on the learning rate.

Methods

__init__

__init__(
    monitor='val_loss',
    factor=0.1,
    patience=10,
    verbose=0,
    mode='auto',
    epsilon=0.0001,
    cooldown=0,
    min_lr=0
)

in_cooldown

in_cooldown()

on_batch_begin

on_batch_begin(
    batch,
    logs=None
)

on_batch_end

on_batch_end(
    batch,
    logs=None
)

on_epoch_begin

on_epoch_begin(
    epoch,
    logs=None
)

on_epoch_end

on_epoch_end(
    epoch,
    logs=None
)

on_train_begin

on_train_begin(logs=None)

on_train_end

on_train_end(logs=None)

set_model

set_model(model)

set_params

set_params(params)