ゼロから作るディープラーニングの５章　TwoLayerNetのgradientについて

#わからないこと
TwoLayerNetにあるgradientメソッドのforwardについて
#TwoLayerNetのコード

python
1# coding: utf-8
2import sys, os
3sys.path.append(os.pardir)  # 親ディレクトリのファイルをインポートするための設定
4import numpy as np
5from common.layers import *
6from common.gradient import numerical_gradient
7from collections import OrderedDict
8
9
10class TwoLayerNet:
11
12    def __init__(self, input_size, hidden_size, output_size, weight_init_std = 0.01):
13        # 重みの初期化
14        self.params = {}
15        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
16        self.params['b1'] = np.zeros(hidden_size)
17        self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size) 
18        self.params['b2'] = np.zeros(output_size)
19
20        # レイヤの生成
21        self.layers = OrderedDict()
22        self.layers['Affine1'] = Affine(self.params['W1'], self.params['b1'])
23        self.layers['Relu1'] = Relu()
24        self.layers['Affine2'] = Affine(self.params['W2'], self.params['b2'])
25
26        self.lastLayer = SoftmaxWithLoss()
27        
28    def predict(self, x):
29        for layer in self.layers.values():
30            x = layer.forward(x)
31        
32        return x
33        
34    # x:入力データ, t:教師データ
35    def loss(self, x, t):
36        y = self.predict(x)
37        return self.lastLayer.forward(y, t)
38    
39    def accuracy(self, x, t):
40        y = self.predict(x)
41        y = np.argmax(y, axis=1)
42        if t.ndim != 1 : t = np.argmax(t, axis=1)
43        
44        accuracy = np.sum(y == t) / float(x.shape[0])
45        return accuracy
46        
47    # x:入力データ, t:教師データ
48    def numerical_gradient(self, x, t):
49        loss_W = lambda W: self.loss(x, t)
50        
51        grads = {}
52        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
53        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
54        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
55        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])
56        
57        return grads
58        
59    def gradient(self, x, t):
60        # forward
61        self.loss(x, t)
62
63        # backward
64        dout = 1
65        dout = self.lastLayer.backward(dout)
66        
67        layers = list(self.layers.values())
68        layers.reverse()
69        for layer in layers:
70            dout = layer.backward(dout)
71
72        # 設定
73        grads = {}
74        grads['W1'], grads['b1'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
75        grads['W2'], grads['b2'] = self.layers['Affine2'].dW, self.layers['Affine2'].db
76
77        return grads

#gradient

python
1def gradient(self, x, t):
2        # forward
3        self.loss(x, t)
4
5        # backward
6        dout = 1
7        dout = self.lastLayer.backward(dout)
8        
9        layers = list(self.layers.values())
10        layers.reverse()
11        for layer in layers:
12            dout = layer.backward(dout)
13
14        # 設定
15        grads = {}
16        grads['W1'], grads['b1'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
17        grads['W2'], grads['b2'] = self.layers['Affine2'].dW, self.layers['Affine2'].db
18
19        return grads