dcase_util.keras.StopperCallback

class dcase_util.keras.StopperCallback(epochs=None, manual_update=False, monitor='val_loss', patience=0, min_delta=0, initial_delay=10, **kwargs)[source]

Keras callback to stop training when improvement has not seen in specified amount of epochs. Implements Keras Callback API.

Callback is very similar to standard EarlyStopping Keras callback, however it adds support for external metrics (calculated outside Keras training process).

Constructor

Parameters
epochsint

Total amount of epochs

manual_updatebool

Manually update callback, use this to when injecting external metrics

monitorstr

Metric value to be monitored

patienceint

Number of epochs with no improvement after which training will be stopped.

min_deltafloat

Minimum change in the monitored quantity to qualify as an improvement.

initial_delayint

Amount of epochs to wait at the beginning before quantity is monitored.

__init__(epochs=None, manual_update=False, monitor='val_loss', patience=0, min_delta=0, initial_delay=10, **kwargs)[source]

Constructor

Parameters
epochsint

Total amount of epochs

manual_updatebool

Manually update callback, use this to when injecting external metrics

monitorstr

Metric value to be monitored

patienceint

Number of epochs with no improvement after which training will be stopped.

min_deltafloat

Minimum change in the monitored quantity to qualify as an improvement.

initial_delayint

Amount of epochs to wait at the beginning before quantity is monitored.

Methods

__init__([epochs, manual_update, monitor, ...])

Constructor

add_external_metric(metric_label)

get_operator(metric)

on_batch_begin(batch[, logs])

on_batch_end(batch[, logs])

on_epoch_begin(epoch[, logs])

on_epoch_end(epoch[, logs])

on_train_begin([logs])

on_train_end([logs])

set_external_metric_value(metric_label, ...)

Add external metric value

set_model(model)

set_params(params)

stop()

update()

Attributes

logger