contrib.keras.optimizers.Nadam

tf.contrib.keras.optimizers.Nadam

class tf.contrib.keras.optimizers.Nadam

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

Nesterov Adam optimizer.

Much like Adam is essentially RMSprop with momentum, Nadam is Adam RMSprop with Nesterov momentum.

Default parameters follow those provided in the paper. It is recommended to leave the parameters of this optimizer at their default values.

Arguments:

lr: float >= 0. Learning rate.
beta_1/beta_2: floats, 0 < beta < 1. Generally close to 1.
epsilon: float >= 0. Fuzz factor.

References: - Nadam report - On the importance of initialization and momentum in deep learning

Methods

__init__

__init__(
    lr=0.002,
    beta_1=0.9,
    beta_2=0.999,
    epsilon=1e-08,
    schedule_decay=0.004,
    **kwargs
)

from_config

from_config(
    cls,
    config
)

get_config

get_config()

get_gradients

get_gradients(
    loss,
    params
)

get_updates

get_updates(
    params,
    constraints,
    loss
)

get_weights

get_weights()

Returns the current value of the weights of the optimizer.

Returns:

A list of numpy arrays.

set_weights

set_weights(weights)

Sets the weights of the optimizer, from Numpy arrays.

Should only be called after computing the gradients (otherwise the optimizer has no weights).

Arguments:

weights: a list of Numpy arrays. The number
    of arrays and their shape must match
    number of the dimensions of the weights
    of the optimizer (i.e. it should match the
    output of `get_weights`).

Raises:

ValueError: in case of incompatible weight shapes.