def get_updates(self, params, constraints, loss):
grads = self.get_gradients(loss, params)
self.updates = [(self.iterations, self.iterations + 1.)]
t = self.iterations + 1
lr_t = self.lr / (1 - K.pow(self.beta_1, t))
for p, g, c in zip(params, grads, constraints):
# zero init of 1st moment
m = K.variable(np.zeros(K.get_value(p).shape))
# zero init of exponentially weighted infinity norm
u = K.variable(np.zeros(K.get_value(p).shape))
m_t = (self.beta_1 * m) + (1 - self.beta_1) * g
u_t = K.maximum(self.beta_2 * u, K.abs(g))
p_t = p - lr_t * m_t / (u_t + self.epsilon)
self.updates.append((m, m_t))
self.updates.append((u, u_t))
self.updates.append((p, c(p_t))) # apply constraints
return self.updates
def get_updates(self, params, constraints, loss):
grads = self.get_gradients(loss, params)
self.updates = [(self.iterations, self.iterations+1.)]
t = self.iterations + 1
lr_t = self.lr / (1 - K.pow(self.beta_1, t))
for p, g, c in zip(params, grads, constraints):
# zero init of 1st moment
m = K.variable(np.zeros(K.get_value(p).shape))
# zero init of exponentially weighted infinity norm
u = K.variable(np.zeros(K.get_value(p).shape))
m_t = (self.beta_1 * m) + (1 - self.beta_1) * g
u_t = K.maximum(self.beta_2 * u, K.abs(g))
p_t = p - lr_t * m_t / (u_t + self.epsilon)
self.updates.append((m, m_t))
self.updates.append((u, u_t))
self.updates.append((p, c(p_t))) # apply constraints
return self.updates
def hinge(y_true, y_pred):
return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)
def squared_hinge(y_true, y_pred):
return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)
def hinge(y_true, y_pred):
return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)
def squared_hinge(y_true, y_pred):
return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)