def __init__(self,
decay_steps,
warmup_steps,
min_lr=0.0,
lr=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=None,
weight_decay=0.,
weight_decay_pattern=None,
amsgrad=False,
**kwargs):
super(AdamWarmup, self).__init__(**kwargs)
with K.name_scope(self.__class__.__name__):
self.decay_steps = K.variable(decay_steps, name='decay_steps')
self.warmup_steps = K.variable(warmup_steps, name='warmup_steps')
self.min_lr = K.variable(min_lr, name='min_lr')
self.iterations = K.variable(0, dtype='int64', name='iterations')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.weight_decay = K.variable(weight_decay, name='weight_decay')
if epsilon is None:
epsilon = K.epsilon()
self.epsilon = epsilon
self.initial_weight_decay = weight_decay
self.weight_decay_pattern = weight_decay_pattern
self.amsgrad = amsgrad
def __init__(self,
center=True,
scale=True,
epsilon=None,
gamma_initializer='ones',
beta_initializer='zeros',
gamma_regularizer=None,
beta_regularizer=None,
gamma_constraint=None,
beta_constraint=None,
**kwargs):
"""Layer normalization layer
See: [Layer Normalization](https://arxiv.org/pdf/1607.06450.pdf)
:param center: Add an offset parameter if it is True.
:param scale: Add a scale parameter if it is True.
:param epsilon: Epsilon for calculating variance.
:param gamma_initializer: Initializer for the gamma weight.
:param beta_initializer: Initializer for the beta weight.
:param gamma_regularizer: Optional regularizer for the gamma weight.
:param beta_regularizer: Optional regularizer for the beta weight.
:param gamma_constraint: Optional constraint for the gamma weight.
:param beta_constraint: Optional constraint for the beta weight.
:param kwargs:
"""
super(LayerNormalization, self).__init__(**kwargs)
self.supports_masking = True
self.center = center
self.scale = scale
if epsilon is None:
epsilon = K.epsilon() * K.epsilon()
self.epsilon = epsilon
self.gamma_initializer = keras.initializers.get(gamma_initializer)
self.beta_initializer = keras.initializers.get(beta_initializer)
self.gamma_regularizer = keras.regularizers.get(gamma_regularizer)
self.beta_regularizer = keras.regularizers.get(beta_regularizer)
self.gamma_constraint = keras.constraints.get(gamma_constraint)
self.beta_constraint = keras.constraints.get(beta_constraint)
self.gamma, self.beta = None, None
