def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) accumulators = [ K.variable(np.zeros(K.get_value(p).shape)) for p in params ] delta_accumulators = [ K.variable(np.zeros(K.get_value(p).shape)) for p in params ] self.updates = [] for p, g, a, d_a, c in zip(params, grads, accumulators, delta_accumulators, constraints): # update accumulator new_a = self.rho * a + (1 - self.rho) * K.square(g) self.updates.append((a, new_a)) # use the new accumulator and the *old* delta_accumulator update = g * K.sqrt(d_a + self.epsilon) / K.sqrt(new_a + self.epsilon) new_p = p - self.lr * update self.updates.append((p, c(new_p))) # apply constraints # update delta_accumulator new_d_a = self.rho * d_a + (1 - self.rho) * K.square(update) self.updates.append((d_a, new_d_a)) return self.updates
def __init__(self, lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=1e-8, *args, **kwargs): super(Adamax, self).__init__(**kwargs) self.__dict__.update(locals()) self.iterations = K.variable(0) self.lr = K.variable(lr) self.beta_1 = K.variable(beta_1) self.beta_2 = K.variable(beta_2)
def __init__(self, lr=0.01, momentum=0., decay=0., nesterov=False, *args, **kwargs): super(SGD, self).__init__(**kwargs) self.__dict__.update(locals()) self.iterations = K.variable(0.) self.lr = K.variable(lr) self.momentum = K.variable(momentum) self.decay = K.variable(decay)
def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params] self.updates = [] for p, g, a, c in zip(params, grads, accumulators, constraints): new_a = a + K.square(g) # update accumulator self.updates.append((a, new_a)) new_p = p - self.lr * g / K.sqrt(new_a + self.epsilon) self.updates.append((p, c(new_p))) # 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 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 * K.sqrt(1 - K.pow(self.beta_2, t)) / (1 - K.pow(self.beta_1, t)) for p, g, c in zip(params, grads, constraints): # zero init of moment m = K.variable(np.zeros(K.get_value(p).shape)) # zero init of velocity v = K.variable(np.zeros(K.get_value(p).shape)) 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 = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon) self.updates.append((m, m_t)) self.updates.append((v, v_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 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 * K.sqrt(1 - K.pow(self.beta_2, t)) / ( 1 - K.pow(self.beta_1, t)) for p, g, c in zip(params, grads, constraints): # zero init of moment m = K.variable(np.zeros(K.get_value(p).shape)) # zero init of velocity v = K.variable(np.zeros(K.get_value(p).shape)) 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 = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon) self.updates.append((m, m_t)) self.updates.append((v, v_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) accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params] delta_accumulators = [K.variable(np.zeros(K.get_value(p).shape)) for p in params] self.updates = [] for p, g, a, d_a, c in zip(params, grads, accumulators, delta_accumulators, constraints): # update accumulator new_a = self.rho * a + (1 - self.rho) * K.square(g) self.updates.append((a, new_a)) # use the new accumulator and the *old* delta_accumulator update = g * K.sqrt(d_a + self.epsilon) / K.sqrt(new_a + self.epsilon) new_p = p - self.lr * update self.updates.append((p, c(new_p))) # apply constraints # update delta_accumulator new_d_a = self.rho * d_a + (1 - self.rho) * K.square(update) self.updates.append((d_a, new_d_a)) return self.updates
def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) accumulators = [ K.variable(np.zeros(K.get_value(p).shape)) for p in params ] self.updates = [] for p, g, a, c in zip(params, grads, accumulators, constraints): new_a = a + K.square(g) # update accumulator self.updates.append((a, new_a)) new_p = p - self.lr * g / K.sqrt(new_a + self.epsilon) self.updates.append((p, c(new_p))) # apply constraints return self.updates
def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) lr = self.lr * (1.0 / (1.0 + self.decay * self.iterations)) self.updates = [(self.iterations, self.iterations + 1.)] for p, g, c in zip(params, grads, constraints): m = K.variable(np.zeros(K.get_value(p).shape)) # momentum v = self.momentum * m - lr * g # velocity self.updates.append((m, v)) if self.nesterov: new_p = p + self.momentum * v - lr * g else: new_p = p + v self.updates.append((p, c(new_p))) # apply constraints return self.updates
def __init__(self, lr=1.0, rho=0.95, epsilon=1e-6, *args, **kwargs): super(Adadelta, self).__init__(**kwargs) self.__dict__.update(locals()) self.lr = K.variable(lr)
def __init__(self, lr=0.01, epsilon=1e-6, *args, **kwargs): super(Adagrad, self).__init__(**kwargs) self.__dict__.update(locals()) self.lr = K.variable(lr)
def __init__(self, lr=0.001, rho=0.9, epsilon=1e-6, *args, **kwargs): super(RMSprop, self).__init__(**kwargs) self.__dict__.update(locals()) self.lr = K.variable(lr) self.rho = K.variable(rho)