chapter 5 误差反向传播法

layer_naive.py

class MulLayer:
    def __init__(self):
        self.x = None
        self.y = None

    def forward(self, x, y):
        self.x = x
        self.y = y

        out = x * y
        return out

    def backward(self, dout):
        dx = dout * self.y
        dy = dout * self.x

        return dx, dy

class AddLayer:
    def __init__(self):
        pass

    def forward(self, x, y):
        out = x + y
        
        return out

    def backward(self, dout):
        dx = dout * 1
        dy = dout * 1
        
        return dx, dy

layers.py

# coding:utf-8
import numpy as nu
from common.functions import *
from common.util import im2col, col2im

class Relu:
    def __init__(self):
        self.mask = None

    def forward(self, x):
        self.mask = (x <= 0)
        out = x.copy()
        out[self.mask] = 0

        return out

    def backward(self, dout):
        dout[self.mask] = 0
        dx = dout
        
        return dx

class Sigmoid:
    def __init__(self):
        self.out = None

    def forward(self, x):
        out sigmoid(x)
        self.out = out
        return out

    def backward(self, dout):
        dx = dout * (1.0 - self.out) * self.out

        return dx

class Affine:
    def __init__(self, W, b):
        self.W = W
        self.b = b

        self.x = None
        self.original_shape = None
        #权重和偏置参数地导数
        self.dW = None
        self.db = None

    def forward(self, x):
        self.original_x_shape = x.shape
        x = x.reshape(x.shape[0],-1)
        self.x = x

        out = np.dot(self.x, self.W) + self.b
        
        return out

    def backward(self, dout):
        dx = np.dot(dout, self.W.T)
        self.dW = np.dot(self.x.T, dout)
        self.db = np.sum(dout, axis=0)

        dx = dx.reshape(*self.original_x_shape)
        return dx

class SoftmaxWithLoss:
    def __init__(self):
        self.loss = None
        self.y = None # softmax 输出
        self.t = None # 监督数据

    def forward(self, x, t):
        self.t = t
        self.y = softmax(x)
        self.loss = cross_entropy_error(self.y, self.t)
        
        return self.loss

    def backward(self,dout=1):
        batch_size = self.t.shape[0]
        if self.t.size == self.y.size: #监督数据是one-hot-vector
            dx = (self.y - self.t) / batch_size
        else:
            dx = self.y.copy()
            dx[np.arange(batch_size), self.t] -=1
            dx = dx /batch_size

        return dx

buy_apple.py

# coding: utf-8
from layer_navie import *

apple = 100
apple_num = 2
tax = 1.1

mul_apple_layer = MulLayer()
mul_tax_layer = MulLayer()

# forward
apple_price = mul_apple_layer.forward(apple, apple_num)
price = mul_tax_layer.forward(apple_price, tax)

# backward
dprice = 1
dapple_price, dtax = mul_tax_layer.backward(dprice)
apple, dapple_num = mul_apple_layer.backward(dapple_price)

print('price:',int(price))
print('dApple:',dapple)
print('dApple_num:',int(dapple_num))
print('dTax:',dtax)

buy_apple_orange.py

# coding: utf-8
from layer_naive import *

apple = 100
apple_num = 2
orange = 150
orange_num = 3
tax = 1.1

# layer
mul_apple_layer = MulLayer()
mul_orange_layer = MulLayer()
add_apple_orange_layer = AddLayer()
mul_tax_layer = MulLayer()

# forward
apple_price = mul_apple_layer.forward(apple, apple_num)
orange_price = mul_orange_layer.forward(orange, orange_num)
all_price = add_apple_orange_layer.forward(apple_price, orange_price)
price = mul_tax_layer.forward(all_price, tax)

# backward
dprice = 1
dall_price, dtax = mul_tax_layer.backward(dprice)
dapple_price, dorange_price = add_apple_orange_layer.backward(dall_price)
dorange, dorange_num = mul_orange_layer.backward(dorange_price)
dapple, dapple_num = mul_apple_layer.backward(dapple_price)

print("price:", int(price))
print("dApple:", dapple)
print("dApple_num:", int(dapple_num))
print("dOrange:", dorange)
print("dOrange_num:", int(dorange_num))
print("dTax:", dtax)

gradient_check.py

# coding: utf-8
import sys, os
sys.path.append(os.pardir)
import numpy as np
from dataset.mnist import load_mnist
from two_layer_net import TwoLayerNet

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

network = TwoLayerNet(input_size=748, hidden_size=50, output_size=10)

x_batch = x_train[:3]
t_batch = t_train[:3]

grad_numerical = network.numerical_gradient(x_batch, t_batch)
grad_backprop = network.gradient(x_batch, t_batch)

for key in grad_numerical.keys():
    diff = np.average(np.abs(grad_backprop[key] - grad_numerical[key])
    print(key + ': ' + str(diff))

train_neural_net.py

# coding: utf-8
import sys, os
sys.path.append(os.pardir)

import numpy as np
from dataset.mnist import load_mnist
from two_layer_net import TwoLayerNet

# 读入数据
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

iters_num = 10000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.1

train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)

for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]
    
    # 梯度
    #grad = network.numerical_gradient(x_batch, t_batch)
    grad = network.gradient(x_batch, t_batch)
    
    # 更新
    for key in ('W1', 'b1', 'W2', 'b2'):
        network.params[key] -= learning_rate * grad[key]
    
    loss = network.loss(x_batch, t_batch)
    train_loss_list.append(loss)
    
    if i % iter_per_epoch == 0:
        train_acc = network.accuracy(x_train, t_train)
        test_acc = network.accuracy(x_test, t_test)
        train_acc_list.append(train_acc)
        test_acc_list.append(test_acc)
        print(train_acc, test_acc)

two_layer_net.py

# coding:utf-8
import sys, os
sys.path.append(os.pardir)
import numpy as np
from common.layers import *
from common.gradient import numerical_gradient
from collections import OrderedDict

class TwoLayerNet:
    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        self.params = {}
        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W1'] = weight_init_std * np.random.randn(hidden_size, output_size)
        self.params['b1'] = np.zeros(output_size)

        self.layers = OrderedDict()
        self.layers['Affine1'] = Affine(self.params['W1'], self.params['b1'])
        self.layers['Relu1'] = Relu()
        self.layers['Affine2'] = Affine(self.params['W2'], self.params['b2'])
        
        self.lastLayer = SoftmaxWithLoss()
    
    def predict(self, x):
        for layer in self.layers.values():
            x = layer.forward(x)
        return x

    def loss(self, x, t):
        y = self.predict(x)
        return self.lastLayer.forward(y, t)

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        if t.ndim !=1 :
            t = np.argmax(t, axis=1)
        accuracy = np.sum(y == t) / float(x.shape[0])

    def numerical_gradient(self, x, t):
        loss_W = lamdba W: self.loss(x, t)

        grads = {}
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])

        return grads

    def gradient(self, x, t):
        # forward
        self.loss(x, t)

        # backward
        dout = 1
        dout = self.lastLayer.backward(dout)
        
        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        grads = {}
        grads['W1'], grads['b1'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
        grads['W2'], grads['b2'] = self.layers['Affine2'].dW, self.layers['Affine2'].db
        
        return grads
        

本章所学内容

1. 通过使用计算图，可以直观地把握计算过程
2. 计算图的节点是由局部计算构成的，局部计算构成全局计算
3. 计算图的正向传播进行一般的计算，通过计算图的反向传播，可以计算各个节点的导数
4. 通过将神经网路的组成元素实现为层，可以高效地计算梯度（反向传播法）
5. 通过比较数值微分和误差反向传播法地结果，可以确认误差反向传播法的实现是否正确（梯度确认）