Skip to content
masterclass Buddy
Start learning

TensorFlow · Class

callbacks.ReduceLROnPlateau

ReduceLROnPlateau lowers the learning rate when a monitored metric stops improving. It waits for a set number of epochs, then applies a multiplier while respecting a minimum learning rate.

Last updated

Syntax

tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=10, verbose=0, mode='auto', min_delta=0.0001, cooldown=0, min_lr=0.0, **kwargs)

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • Callback
  • EarlyStopping
  • LearningRateScheduler
  • ModelCheckpoint
  • History

Source: tf.keras.callbacks.ReduceLROnPlateau | TensorFlow v2.21.0. Checked 2026-11-03.