04_面向对象的网络

import numpy as np


# 激活函数
def activation_relu(input):
    return np.maximum(0, input)

# 定义一个层类
class Layer():
    def __init__(self, n_inputs, n_neurons):
        self.weights = np.random.randn(n_inputs, n_neurons)
        self.biases = np.random.randn(n_neurons)

    def layer_forward(self, inputs):
        sum1 = np.dot(inputs, self.weights) + self.biases
        output = activation_relu(sum1)
        return output

# 定义一个网络类
class Network():
    def __init__(self, network_shape):
        self.shape = network_shape
        self.layers = []
        for i in range(len(network_shape) - 1):
            layer = Layer(network_shape[i], network_shape[i+1])
            self.layers.append(layer)
    # 前馈运算函数
    def network_forward(self, inputs):
        outputs = [inputs]
        for i in range(len(self.layers)):
            layer_output = self.layers[i].layer_forward(outputs[i])
            outputs.append(layer_output)
        print(outputs)
        return outputs










#-------------------------------Test----------------------------------
def test():
    a1 = -0.9
    a2 = 0.5
    a3 = 0.7
    input1 = np.array([[a1, a2, a3],
                       [-a1, -a2, -a3]])
    network_shape = [3, 4, 5, 3]

    network = Network(network_shape)
    network.network_forward(input1)

#-------------------------------运行-----------------------------------
test()