Base Optimizer API These methods and attributes are common to all Keras optimizers. [source] Optimizer class keras.optimizers.Optimizer()

Optimizers SGD RMSprop Adam AdamW Adadelta Adagrad Adamax Adafactor Nadam Ftrl [source] apply_gradients method Optimizer.apply_gradients( grads_and_vars, name=None, …

learning_rate: A float, a keras.optimizers.schedules.LearningRateSchedule instance, or a callable that takes no arguments and returns the actual value to use.

learning_rate: A float, a keras.optimizers.schedules.LearningRateSchedule instance, or a callable that takes no arguments and returns the actual value to use.

learning_rate: A float, a keras.optimizers.schedules.LearningRateSchedule instance, or a callable that takes no arguments and returns the actual value to use.

learning_rate: A float, a keras.optimizers.schedules.LearningRateSchedule instance, or a callable that takes no arguments and returns the actual value to use.

If the argument staircase is True, then step / decay_steps is an integer division and the decayed learning rate follows a staircase function. You can pass this schedule directly into a …

learning_rate: A float, keras.optimizers.schedules.LearningRateSchedule instance, or a callable that takes no arguments and returns the actual value to use. The learning rate.

Several built-in learning rate schedules are available, such as keras.optimizers.schedules.ExponentialDecay or keras.optimizers.schedules.PiecewiseConstantDecay:

If wrapping a tf.keras.optimizers.Optimizer, hyperparameters can be accessed and set on the LossScaleOptimizer, which will be delegated to the wrapped optimizer.