|TensorFlow 1 version||View source on GitHub|
Stop training when a monitored metric has stopped improving.
Compat aliases for migration
See Migration guide for more details.
tf.keras.callbacks.EarlyStopping( monitor='val_loss', min_delta=0, patience=0, verbose=0, mode='auto', baseline=None, restore_best_weights=False )
Used in the notebooks
|Used in the guide||Used in the tutorials|
Assuming the goal of a training is to minimize the loss. With this, the
metric to be monitored would be
'loss', and mode would be
model.fit() training loop will check at end of every epoch whether
the loss is no longer decreasing, considering the
patience if applicable. Once it's found no longer decreasing,
model.stop_training is marked True and the training terminates.
The quantity to be monitored needs to be available in
To make it so, pass the loss or metrics at
||Quantity to be monitored.|
||Minimum change in the monitored quantity to qualify as an improvement, i.e. an absolute change of less than min_delta, will count as no improvement.|
||Number of epochs with no improvement after which training will be stopped.|
||Baseline value for the monitored quantity. Training will stop if the model doesn't show improvement over the baseline.|
Whether to restore model weights from
the epoch with the best value of the monitored quantity.
If False, the model weights obtained at the last step of
training are used. An epoch will be restored regardless
of the performance relative to the
callback = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=3)
# This callback will stop the training when there is no improvement in
# the loss for three consecutive epochs.
model = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])
history = model.fit(np.arange(100).reshape(5, 20), np.zeros(5),
epochs=10, batch_size=1, callbacks=[callback],
len(history.history['loss']) # Only 4 epochs are run.
get_monitor_value( logs )
set_model( model )
set_params( params )