python实现BackPropagation算法

def backprop(self,x,y):
  nabla_b = [np.zeros(b.shape) for b in self.biases]
  nabla_w = [np.zeros(w.shape) for w in self.weights]
  # 通过输入x，前向计算输出层的值
  activation = x
  activations = [x]# 存储的是所以的输出层
  zs = []
  for b,w in zip(self.biases,self.weights):
    z = np.dot(w,activation)+b
    zs.append(z)
    activation = sigmoid(z)
    activations.append(activation)
  # 计算输出层的error
  delta = self.cost_derivative(activations[-1],y)*sigmoid_prime(zs[:-1])
  nabla_b[-1] = delta
  nabla_w[-1] = np.dot(delta,activations[-2].transpose())
  #反向更新error
  for l in xrange(2,self.num_layers):
    z = zs[-l]
    sp = sigmoid_prime(z)
    delta = np.dot(self.weight[-l+1].transpose(),delta)*sp
    nabla_b[-l] = delta
    nabla_w[-l] = np.dot(delta,activations[-l-1].transpose())
  return (nabla_b,nabla_w)

def cost_derivative(self,output_activation,y):
  return (output_activation-y)
def sigmoid(z):
  return 1.0/(1.0+np.exp(z))
def sigmoid_prime(z):
  return sigmoid(z)*(1-sigmoid(z))