我们从Python开源项目中，提取了以下7个代码示例，用于说明如何使用keras.backend.get_variable_shape()。
def get_weightnorm_params_and_grads(p, g): ps = K.get_variable_shape(p) # construct weight scaler: V_scaler = g/||V|| V_scaler_shape = (ps[-1],) # assumes we're using tensorflow! V_scaler = K.ones(V_scaler_shape) # init to ones, so effective parameters don't change # get V parameters = ||V||/g * W norm_axes = [i for i in range(len(ps) - 1)] V = p / tf.reshape(V_scaler, [1] * len(norm_axes) + [-1]) # split V_scaler into ||V|| and g parameters V_norm = tf.sqrt(tf.reduce_sum(tf.square(V), norm_axes)) g_param = V_scaler * V_norm # get grad in V,g parameters grad_g = tf.reduce_sum(g * V, norm_axes) / V_norm grad_V = tf.reshape(V_scaler, [1] * len(norm_axes) + [-1]) * \ (g - tf.reshape(grad_g / V_norm, [1] * len(norm_axes) + [-1]) * V) return V, V_norm, V_scaler, g_param, grad_g, grad_V
def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) self.updates = [K.update_add(self.iterations, 1)] lr = self.lr if self.initial_decay > 0: lr *= (1. / (1. + self.decay * self.iterations)) shapes = [K.get_variable_shape(p) for p in params] ms = [K.zeros(shape) for shape in shapes] vs = [K.zeros(shape) for shape in shapes] mems = [K.zeros(shape) for shape in shapes] self.weights = [self.iterations] + ms + vs + mems for p, g, m, v, mem in zip(params, grads, ms, vs, mems): r = 1. / (1. + mem) m_t = (1. - r) * m + r * g v_t = (1. - r) * v + r * K.square(g) denoise = K.square(m_t) / (v_t + self.epsilon) p_t = p - g * K.minimum(lr, denoise) / (K.sqrt(v_t) + self.epsilon) mem_t = 1. + mem * (1. - denoise) self.updates.append(K.update(m, m_t)) self.updates.append(K.update(v, v_t)) self.updates.append(K.update(mem, mem_t)) new_p = p_t # apply constraints if p in constraints: c = constraints[p] new_p = c(new_p) self.updates.append(K.update(p, new_p)) return self.updates
def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) self.updates = [K.update_add(self.iterations, 1)] shapes = [K.get_variable_shape(p) for p in params] ms = [K.zeros(shape) for shape in shapes] vs = [K.zeros(shape) for shape in shapes] mems = [K.zeros(shape) for shape in shapes] denoises = [K.zeros(shape) for shape in shapes] self.weights = [self.iterations] + ms + vs + mems + denoises for p, g, m, v, mem, denoise in zip(params, grads, ms, vs, mems, denoises): r = K.minimum(0.2, K.maximum(0.005, 1. / (1. + mem))) mem_t = 1. / r - 1. m_t = (1. - r) * m + r * g v_t = (1. - r) * v + r * K.square(g) denoise_t = 0.99 * denoise + 0.01 * K.square(m_t) / (v_t + self.epsilon) p_t = p - g * denoise_t / (K.sqrt(v_t) + self.epsilon) mem_t = K.maximum(0., 1. + mem_t * (1. - denoise_t)) self.updates.append(K.update(m, m_t)) self.updates.append(K.update(v, v_t)) self.updates.append(K.update(mem, mem_t)) self.updates.append(K.update(denoise, denoise_t)) new_p = p_t # apply constraints if p in constraints: c = constraints[p] new_p = c(new_p) self.updates.append(K.update(p, new_p)) return self.updates
def add_weightnorm_param_updates(updates, new_V_param, new_g_param, W, V_scaler): ps = K.get_variable_shape(new_V_param) norm_axes = [i for i in range(len(ps) - 1)] # update W and V_scaler new_V_norm = tf.sqrt(tf.reduce_sum(tf.square(new_V_param), norm_axes)) new_V_scaler = new_g_param / new_V_norm new_W = tf.reshape(new_V_scaler, [1] * len(norm_axes) + [-1]) * new_V_param updates.append(K.update(W, new_W)) updates.append(K.update(V_scaler, new_V_scaler)) # data based initialization for a given Keras model
def get_updates(self, params, constraints, loss): grads = self.get_gradients(loss, params) self.updates = [K.update_add(self.iterations, 1)] lr = self.lr if self.inital_decay > 0: lr *= (1. / (1. + self.decay * self.iterations)) t = self.iterations + 1 lr_t = lr * K.sqrt(1. - K.pow(self.beta_2, t)) / (1. - K.pow(self.beta_1, t)) shapes = [K.get_variable_shape(p) for p in params] ms = [K.zeros(shape) for shape in shapes] vs = [K.zeros(shape) for shape in shapes] f = K.variable(0) d = K.variable(1) self.weights = [self.iterations] + ms + vs + [f, d] cond = K.greater(t, K.variable(1)) small_delta_t = K.switch(K.greater(loss, f), self.small_k + 1, 1. / (self.big_K + 1)) big_delta_t = K.switch(K.greater(loss, f), self.big_K + 1, 1. / (self.small_k + 1)) c_t = K.minimum(K.maximum(small_delta_t, loss / (f + self.epsilon)), big_delta_t) f_t = c_t * f r_t = K.abs(f_t - f) / (K.minimum(f_t, f)) d_t = self.beta_3 * d + (1 - self.beta_3) * r_t f_t = K.switch(cond, f_t, loss) d_t = K.switch(cond, d_t, K.variable(1.)) self.updates.append(K.update(f, f_t)) self.updates.append(K.update(d, d_t)) 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 = p - lr_t * m_t / (d_t * K.sqrt(v_t) + self.epsilon) self.updates.append(K.update(m, m_t)) self.updates.append(K.update(v, v_t)) new_p = p_t # apply constraints if p in constraints: c = constraints[p] new_p = c(new_p) self.updates.append(K.update(p, new_p)) return self.updates
