MNIST手写数字识别总结(pytorch)

此博客并不是教程，只是一个练习总结
代码汇总放在文末

1.首先导入所需要的库

import torch
from torch import nn
from torch.nn import functional as F
from torch import optim
import torchvision

from matplotlib import pyplot as plt
import pandas as pd
import numpy as np

from Util import plot_image,pd_one_hot #辅助函数，在博客末尾附上

2.数据集

此数据集总共包含70K张图片，其中60K作为训练集，10K作为测试集。
更多消息可以查看官网官网链接：官网

3.加载数据

batch_size设置一次处理多少图片，此处设置为512张图片，这样并行处理可以cpu，gpu加快处理速度

batch_size = 512

加载训练集，测试集图片

train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_data'      #数据集文件夹名
                               ,train=True
                               ,download=True    #当电脑没此数据的时候会自动下载数据集
                               ,transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor()        #矩阵转化为张量
                                  ,torchvision.transforms.Normalize((0.1307,), (0.3081,))
                               ])
                              )
    ,batch_size=batch_size
    ,shuffle=True              # 设置随机打散
)

test_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_data'
                               ,train=False
                               ,download=True
                               ,transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor()
                                  ,torchvision.transforms.Normalize((0.1307,), (0.3081,))
                               ])
                              ),
    batch_size=batch_size
   ,shuffle=False)

4.数据可视化

只查看9张图片，可在辅助函数内修改为其它值

x, y = next(iter(train_loader))
print(x.shape, y.shape)		# 查看数据集大小
plot_image(x, y, 'image sample')

torch.Size([512, 1, 28, 28]) torch.Size([512])

注：
512, 1, 28, 28:四维矩阵，512张图片，1个通道，大小为28*28
1个通道的意思为单色，若改为3则是RGB彩色

5.定义神经网络

class Net(nn.Module):
    
    def __init__(self):
        super(Net , self).__init__()
        
        self.fc1 = nn.Linear(28*28 , 256)  # 输入和输出的维度，根据经验自己设置
        self.fc2 = nn.Linear(256 , 64)	   # 输入维度要等于上层的输出维度
        self.fc3 = nn.Linear(64 , 10)      # 数字结果为0~9，所以最后输出值为10个维度
        
    def forward(self , x):
        x = F.relu(self.fc1(x))			   # relu 激活函数
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

6.训练测试集

1.初始化网络

net = Net()

2.设置学习率

optimizer = optim.SGD(net.parameters() , lr = 0.01 , momentum= 0.9)

3.迭代

此处没有调用GPU处理数据

loss_s = [ ]   # 存储损失值
for each in range(3):	# 迭代三次
    for location , (x,y) in enumerate(train_loader):
        x = x.view(x.size(0) , 28*28)    #将图片矩阵打平
        out = net(x)
        y_onehot = pd_one_hot(y)
        
        loss = F.mse_loss(out , torch.from_numpy(y_onehot).float())
        
        # 清零梯度
        optimizer.zero_grad()
        # 计算梯度
        loss.backward()
        # 更新梯度
        optimizer.step()
        
        if(location % 5 == 0):    # 每处理5*512张图片记录一次损失函数值
            loss_s.append(loss.item())	# .item的意思为只输出值
    print('第' , each+1 , '次迭代完成')

第 1 次迭代完成
第 2 次迭代完成
第 3 次迭代完成

4.查看损失值

plt.plot(range(len(loss_s)) , loss_s , 'y')
plt.show()

损失值递减且趋于稳定，训练过程正确

7.预测训练集

# 存储预测正确图片的数量
total_correct = 0

for x,y in test_loader:
    x  = x.view(x.size(0), 28*28)
    out = net(x)
    pred = out.argmax(dim=1)	# 取最大值概率所在的位置
    correct = pred.eq(y).sum().float().item()
    total_correct += correct

print('正确率：' , total_correct/len(test_loader.dataset))

正确率： 0.8903

8.查看测试集图片

x , y = next(iter(test_loader))
plot_image(x , y , 'test')

---

---

---

Util.py代码

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

def plot_image(img, label, name):
    fig = plt.figure()
    for i in range(9):
        plt.subplot(3, 3, i + 1)
        plt.tight_layout()
        plt.imshow(img[i][0] * 0.3081 + 0.1307, cmap='gray', interpolation='none')
        plt.title("{}: {}".format(name, label[i].item()))
        plt.xticks([])
        plt.yticks([])
    plt.show()


def pd_one_hot(y):
    y = y.reshape(-1 , 1)	
    y = pd.Series(y)		# 使用pandas的one-hot处理
    y= y.astype(str)
    y = pd.get_dummies(y)
    return y.values

---

---

---

正文代码汇总

项目github链接: github.com/2979083263/mnist

import torch
from torch import nn
from torch.nn import functional as F
from torch import optim
import torchvision

from matplotlib import pyplot as plt
import pandas as pd
import numpy as np


from Util import plot_curve,plot_image,one_hot,pd_one_hot


batch_size = 512

train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_data'
                               , train=True
                               ,download=True
                               ,transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor()        #矩阵转化为张量
                                  ,torchvision.transforms.Normalize((0.1307,), (0.3081,))
                               ])
                              )
    ,batch_size=batch_size
    ,shuffle=True              # 设置随机打散
)

test_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_data'
                               ,train=False
                               ,download=True
                               ,transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor()
                                  ,torchvision.transforms.Normalize((0.1307,), (0.3081,))
                               ])
                              ),
    batch_size=batch_size
    ,shuffle=False)


x, y = next(iter(train_loader))   #暂时看作迭代
print(x.shape, y.shape, x.min(), x.max())
plot_image(x, y, 'image sample')


class Net(nn.Module):
    
    def __init__(self):
        super(Net , self).__init__()
        
        self.fc1 = nn.Linear(28*28 , 256)  #输入和输出的维度
        self.fc2 = nn.Linear(256 , 64)
        self.fc3 = nn.Linear(64 , 10)
        
    def forward(self , x):
        
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        
        return x

net = Net()


optimizer = optim.SGD(net.parameters() , lr = 0.01 , momentum= 0.9)


loss_s = [ ]


for each in range(3):
    for location , (x,y) in enumerate(train_loader):
        x = x.view(x.size(0) , 28*28)
        out = net(x)
        y_onehot = pd_one_hot(y)
        
        loss = F.mse_loss(out , torch.from_numpy(y_onehot).float())
        
        # 清零梯度
        optimizer.zero_grad()
        # 计算梯度
        loss.backward()
        # 更新梯度
        optimizer.step()
        
        if(location % 5 == 0):
            loss_s.append(loss.item())
    print('第' , each+1 , '次迭代完成')

plt.plot(range(len(loss_s)) , loss_s , 'y')
plt.show()


# 存储正确的数量
total_correct = 0


for x,y in test_loader:
    x  = x.view(x.size(0), 28*28)
    out = net(x)
    # out: [b, 10] => pred: [b]
    pred = out.argmax(dim=1)
    correct = pred.eq(y).sum().float().item()
    total_correct += correct

print('正确率：' , total_correct/len(test_loader.dataset))

x , y = next(iter(test_loader))
plot_image(x , y , 'test')