1 class Adam(Optimizer):
 2     '''Adam optimizer.
 3 
 4     Default parameters follow those provided in the original paper.
 5 
 6     # Arguments
 7         lr: float >= 0. Learning rate.
 8         beta_1/beta_2: floats, 0 < beta < 1. Generally close to 1.
 9         epsilon: float >= 0
 
. Fuzz factor.
10 
11     # References
12         - [Adam - A Method for Stochastic Optimization](http://arxiv.org/abs/1412.6980v8)
13     '''
14     def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999,
15                  epsilon=1e-8, decay=0., **kwargs):
16         super(Adam, self).__init__(**kwargs)
17         self.__dict__.update(locals())
 
18         self.iterations = K.variable(0)
19         self.lr = K.variable(lr)
20         self.beta_1 = K.variable(beta_1)
21         self.beta_2 = K.variable(beta_2)
22         self.decay = K.variable(decay)
23         self.inital_decay = decay
24 
25     def get_updates(self, params, constraints, loss):
 
26         grads = self.get_gradients(loss, params)
27         self.updates = [K.update_add(self.iterations, 1)]
28 
29         lr = self.lr
30         if self.inital_decay > 0:
31             lr *= (1. / (1. + self.decay * self.iterations))
32 
33         t = self.iterations + 1
34         lr_t = lr * K.sqrt(1. - K.pow(self.beta_2, t)) / (1. - K.pow(self.beta_1, t))
35 
36         shapes = [K.get_variable_shape(p) for p in params]
37         ms = [K.zeros(shape) for shape in shapes]
38         vs = [K.zeros(shape) for shape in shapes]
39         self.weights = [self.iterations] + ms + vs
40 
41         for p, g, m, v in zip(params, grads, ms, vs):
42             m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
43             v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(g)
44             p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
45 
46             self.updates.append(K.update(m, m_t))
47             self.updates.append(K.update(v, v_t))
48 
49             new_p = p_t
50             # apply constraints
51             if p in constraints:
52                 c = constraints[p]
53                 new_p = c(new_p)
54             self.updates.append(K.update(p, new_p))
55         return self.updates
56 
57     def get_config(self):
58         config = {'lr': float(K.get_value(self.lr)),
59                   'beta_1': float(K.get_value(self.beta_1)),
60                   'beta_2': float(K.get_value(self.beta_2)),
61                   'decay': float(K.get_value(self.decay)),
62                   'epsilon': self.epsilon}
63         base_config = super(Adam, self).get_config()
64         return dict(list(base_config.items()) + list(config.items()))