代码如下:【代码下面是分析】
# -*- coding: utf-8 -*-
"""
Created on Thu Oct 20 16:32:17 2022
@author: w'h'n
"""
import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import numpy as np
import matplotlib.pyplot as plt
from ch03.dataset.mnist import load_mnist
#激活函数
def sigmoid(x):
return 1 / (1 + np.exp(-x))
#激活函数的导数
def sigmoid_grad(x):
return (1.0 - sigmoid(x)) * sigmoid(x)
#相当于求概率,哪个概率大,就预测结果为概率大的索引
def softmax(x):
if x.ndim == 2:
x = x.T
x = x - np.max(x, axis=0)
y = np.exp(x) / np.sum(np.exp(x), axis=0)
return y.T
x = x - np.max(x) # 溢出对策
return np.exp(x) / np.sum(np.exp(x))
#交叉熵误差
def cross_entropy_error(y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
#print('y:',y)
# 监督数据是one-hot-vector的情况下,转换为正确解标签的索引
if t.size == y.size:
t = t.argmax(axis=1)
# print('t:',t)
batch_size = y.shape[0]
#print('y.shape[0]:',y.shape[0])
#print('y[np.arange(batch_size), t]:',y[np.arange(batch_size), t])
return -np.sum(np.log(y[np.arange(batch_size), t] + 1e-7)) / batch_size
def _numerical_gradient_no_batch(f, x):
h = 1e-4 # 0.0001
grad = np.zeros_like(x)
for idx in range(x.size):
tmp_val = x[idx]
x[idx] = float(tmp_val) + h
fxh1 = f(x) # f(x+h)
x[idx] = tmp_val - h
fxh2 = f(x) # f(x-h)
grad[idx] = (fxh1 - fxh2) / (2*h)
x[idx] = tmp_val # 还原值
return grad
#梯度,数值微分
def numerical_gradient(f, X):
if X.ndim == 1:
return _numerical_gradient_no_batch(f, X)
else:
grad = np.zeros_like(X)
for idx, x in enumerate(X):
grad[idx] = _numerical_gradient_no_batch(f, x)
return grad
#数据
class TwoLayerNet:
def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
# 初始化权重
self.params = {}
self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
self.params['b1'] = np.zeros(hidden_size)
self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size)
self.params['b2'] = np.zeros(output_size)
def predict(self, x):
W1, W2 = self.params['W1'], self.params['W2']
b1, b2 = self.params['b1'], self.params['b2']
a1 = np.dot(x, W1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = softmax(a2)
return y
# x:输入数据, t:监督数据
def loss(self, x, t):
y = self.predict(x)
return cross_entropy_error(y, t)
def accuracy(self, x, t):
y = self.predict(x)
y = np.argmax(y, axis=1)
t = np.argmax(t, axis=1)
accuracy = np.sum(y == t) / float(x.shape[0])
return accuracy
# x:输入数据, t:监督数据
def numerical_gradient(self, x, t):
loss_W = lambda 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
##反向误差传播法
'''def gradient(self, x, t):
W1, W2 = self.params['W1'], self.params['W2']
b1, b2 = self.params['b1'], self.params['b2']
grads = {}
batch_num = x.shape[0]
# forward
a1 = np.dot(x, W1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = softmax(a2)
# backward
dy = (y - t) / batch_num
grads['W2'] = np.dot(z1.T, dy)
grads['b2'] = np.sum(dy, axis=0)
da1 = np.dot(dy, W2.T)
dz1 = sigmoid_grad(a1) * da1
grads['W1'] = np.dot(x.T, dz1)
grads['b1'] = np.sum(dz1, axis=0)
return grads'''
# 读入数据
1、加载数据集(以字典的形式存放数据)
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)
network = TwoLayerNet(input_size = 784, hidden_size=100 , output_size=10, weight_init_std=0.01)
iters_num = 10000 # 适当设定循环的次数
train_size = x_train.shape[0]
2、随机选择批数据(100批)
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]
# 计算梯度
grad = network.numerical_gradient(x_batch, t_batch)
#grad = network.gradient(x_batch, t_batch)
# 更新参数
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 | " + str(train_acc) + ", " + str(test_acc))
# 绘制图形
markers = {'train': 'o', 'test': 's'}
x = np.arange(len(train_acc_list))
plt.plot(x, train_acc_list, label='train acc')
plt.plot(x, test_acc_list, label='test acc', linestyle='--')
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()
1、加载数据集(以字典的形式存放数据)
2、随机选择批数据(100批)
3、进行类参数初始化(设置输入层数量、隐含层的权重和偏置、输出层数量、学习率)
4、以批数据遍历
5、调用类方法求梯度network.numerical_gradient(实参:训练数据、one_hot正确解标签)——(1)传给梯度函数numerical_gradient(实参:损失函数、权重/或偏置)——(2)改变权重/或偏置的值(此时起初的类参数初始化的权重/或偏置已经发生变化),这会影响训练数据和one_hot正确解标签的计算——(3)转到损失函数loss(实参:训练数据即输入神经元、正确解标签)【代码以lambda的形式】——(4)转到predict()函数将输入神经元数据和权重、偏置以矩阵运算形式进行神经网络的计算,返回预测概率(100,10)——(5)转到交叉熵误差函数cross_entropy_error(实参:预测概率、正确解标签(100,10))这里计算的是单个数据的平均交叉熵误差,返回一个误差值——(6)这个误差值一直返回给损失函数,再一次改变权重/或偏置的值计算一个误差值返回给损失函数——(7)两个误差值进行数值微分求梯度,返回梯度值给梯度函数numerical_gradient()传进字典中,接着返回给类方法求梯度函数network.numerical_gradient()——(8)依次更新权重和偏置的梯度——(9)进行输入神经元数据与权重偏置参数的矩阵运算,跟one_hot正确解求误差,放进训练数据误差列表中——(10)当达到训练完一批数据时,调用类计算准确率方法计算训练数据和测试数据的准确率。