import keras
from keras import backend as K
class Adam(keras.optimizers.Optimizer):
def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999, **kwargs):
super(Adam, self).__init__(**kwargs)
with K.name_scope(self.__class__.__name__):
self.iterations = K.variable(0, dtype='int64', name='iterations')
self.learning_rate = 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.epsilon = K.epsilon()
def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
self.updates = [K.update_add(self.iterations, 1)]
t = K.cast(self.iterations, K.floatx()) + 1
lr_t = self.learning_rate * (K.sqrt(1. - K.pow(self.beta_2, t)) / (1. - K.pow(self.beta_1, t)))
ms = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]
vs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]
self.weights = [self.iterations] + ms + vs
for p, g, m, v in zip(params, grads, ms, vs):
m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(g)
p_t = lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
self.updates.append(K.update(m, m_t))
self.updates.append(K.update(v, v_t))
self.updates.append(K.update_sub(p, p_t))
return self.updates
