• 以前只知道反向传播通过链式法则实现
• 今天看书发现图片上求出来的值自己算不出来
• 所以自己算了一下，记录一下，并运行了书中的代码
• 相关书籍：[图灵程序设计丛书].深度学习入门：基于Python的理论与实现

1. 相关习题

2. 推导流程

2.1 相关公式

$$\begin{array}{rl}f& =a\ast b\\ g& =c\ast d\\ h& =f+g\\ & =a\ast b+c\ast d\\ i& =h\ast e\\ & =(f+g)\ast e\\ & =(a\ast b+c\ast d）\ast e\end{array}$$

2.3 变量导数求解

• i

  • 最后一层的导数，初始化为1

• e
  $$\begin{array}{rl}\frac{\partial i}{\partial e}& =\frac{\partial i}{\partial i}\ast \frac{\partial i}{\partial e}\\ & =\frac{\partial i}{\partial i}\ast \frac{\partial h\ast e}{\partial e}\\ & =1\ast h\\ & =a\ast b+c\ast d\\ & =2\ast 100+150\ast 3\\ & =650\end{array}$$

• h
  $$\begin{array}{rl}\frac{\partial i}{\partial h}& =\frac{\partial i}{\partial i}\ast \frac{\partial i}{\partial h}\\ & =\frac{\partial i}{\partial i}\ast \frac{\partial h\ast e}{\partial h}\\ & =1\ast e\\ & =1.1\end{array}$$

• f 和 g

  • 因为$h=f+g$,所以反向传播时，相加的位置，直接将导数传过去即可
  • 所以f和g的导数都为1.1

• a
  $$\begin{array}{rl}\frac{\partial f}{\partial a}& =\frac{\partial f}{\partial f}\ast \frac{\partial a\ast b}{\partial a}\\ & =1.1\ast b\\ & =1.1\ast 100\\ & =110\end{array}$$

• b
  $$\begin{array}{rl}\frac{\partial f}{\partial b}& =\frac{\partial f}{\partial f}\ast \frac{\partial f}{\partial b}\\ & =1.1\ast \frac{\partial a\ast b}{\partial b}\\ & =1.1\ast a\\ & =1.1\ast 2\\ & =2.2\end{array}$$

• c
  $$\begin{array}{rl}\frac{\partial g}{\partial c}& =\frac{\partial g}{\partial g}\ast \frac{\partial g}{\partial c}\\ & =1.1\ast \frac{\partial c\ast d}{\partial c}\\ & =1.1\ast d\\ & =1.1\ast 3\\ & =3.3\end{array}$$

• d
  $$\begin{array}{rl}\frac{\partial g}{\partial d}& =\frac{\partial g}{\partial g}\ast \frac{\partial g}{\partial d}\\ & =1.1\ast \frac{\partial c\ast d}{\partial d}\\ & =1.1\ast c\\ & =1.1\ast 150\\ & =165\end{array}$$

3. 代码实现

3.1 参数对应

参数	代码参数
a	dapple_num
b	dapple
c	dorange
d	dorange_num
e	dall_price
f	dapple_price
g	dorange_price
h	dall_price
i	dprice

3.2 代码实现

• 相关代码

  # 乘法类
  class MulLayer:def __init__(self):self.x = Noneself.y = Nonedef forward(self, x, y):""":param x: 价格:param y: 数量 或 税:return: 总价"""self.x = xself.y = yout = x * yreturn outdef backward(self, dout):dx = dout * self.ydy = dout * self.xreturn dx, dyclass AddLayer:def __init__(self):passdef forward(self, x, y):"""价格相加:param x: 苹果总价:param y: 句子总价:return: 总价"""out = x + yreturn outdef backward(self, dout):"""相加的求导直接传递，相当于乘以1:param dout: 导数:return:"""dx = dout * 1dy = dout * 1return dx, dyif __name__ == '__main__':apple,apple_num = 100,2orange,orange_num = 150,3tax = 1.1# 实例化类 layermul_apple_layer = MulLayer()                                            # 计算苹果的价格mul_orange_layer = MulLayer()                                           # 计算橘子的价格add_apple_orange_layer = AddLayer()                                     # 价格相加mul_tax_layer = MulLayer()                                              # 计算税后价格# 前向传播 forwardapple_price = mul_apple_layer.forward(apple, apple_num)                 # 苹果价格*苹果数量orange_price = mul_orange_layer.forward(orange, orange_num)             # 橘子价格*橘子数量all_price = add_apple_orange_layer.forward(apple_price, orange_price)   # 苹果总价+句子总价price = mul_tax_layer.forward(all_price, tax)                           # 计算税后价格# 反向传播 backwarddprice = 1dall_price, dtax = mul_tax_layer.backward(dprice)dapple_price, dorange_price = add_apple_orange_layer.backward(dall_price)dapple, dapple_num = mul_apple_layer.backward(dapple_price)dorange, dorange_num = mul_orange_layer.backward(dorange_price)# 总价print("price:", int(price))print("dprice:", dprice)print("dtax:", dtax)print("dall_price:", dall_price)# 苹果print("dapple_price:", dapple_price)print("dapple_num:", int(dapple_num))print("dapple:", dapple)# 橘子print("dorange_price:", dorange_price)print("dorange_num:", int(dorange_num))print("dorange:", dorange)
  

• 结果