PyTorch练手项目二:MNIST手写数字识别

本文目的:展示如何利用PyTorch进行手写数字识别。

1 导入相关库,定义一些参数

import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

#定义一些参数
BATCH_SIZE = 64
EPOCHS = 10
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

2 准备数据

使用Pytorch自带数据集。

#图像预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
    ])

#训练集
train_set = datasets.MNIST('data', train=True, transform=transform, download=True)
train_loader = DataLoader(train_set, 
                          batch_size=BATCH_SIZE,
                          shuffle=True)

#测试集
test_set = datasets.MNIST('data', train=False, transform=transform, download=True)
test_loader = DataLoader(test_set,
                        batch_size=BATCH_SIZE,
                        shuffle=True)

3 准备模型

#搭建模型
class ConvNet(nn.Module):
    #图像输入是(batch,1,28,28)
    def __init__(self):
        super().__init__() 
        self.conv1 = nn.Conv2d(1, 10, (3,3)) #输入通道数为1,输出通道数为10,卷积核(3,3)
        self.conv2 = nn.Conv2d(10, 32, (3,3))
        self.fc1 = nn.Linear(12*12*32, 100)
        self.fc2 = nn.Linear(100, 10)
    
    def forward(self, x):
        x = self.conv1(x) #(batch,10,26,26)
        x = F.relu(x)
        
        x = self.conv2(x) #(batch,32,24,24)
        x = F.relu(x)
        x = F.max_pool2d(x, (2,2))  #(batch,32,12,12)
        
        x = x.view(x.size(0), -1) #flatten (batch,12*12*32)
        x = self.fc1(x) #(batch,100)
        x = F.relu(x)
        x = self.fc2(x) #(batch,10)
        
        out = F.log_softmax(x, dim=1) #softmax激活并取对数,数值上更稳定
        return out

4 训练

#定义模型和优化器
model = ConvNet().to(DEVICE) #模型移至GPU
optimizer = torch.optim.Adam(model.parameters()) 


#定义训练函数
def train(model, device, train_loader, optimizer, epoch): #跑一个epoch
    model.train()  #开启训练模式,即启用BatchNormalization和Dropout等
    for batch_idx, (data, target) in enumerate(train_loader): #每次产生一个batch
        data, target = data.to(device), target.to(device) #产生的数据移至GPU
        output = model(data) 
        loss = F.nll_loss(output, target) #CrossEntropyLoss = log_softmax + NLLLoss
        optimizer.zero_grad() #所有梯度清零
        loss.backward() #反向传播求所有参数梯度
        optimizer.step() #沿负梯度方向走一步
        if(batch_idx+1) % 234 == 0: 
            print('Train Epoch: {} [{}/{} ({:.1f}%)]\tLoss: {:.6f}'.format(
                epoch, (batch_idx+1) * len(data), len(train_loader.dataset),
                100. * (batch_idx+1) / len(train_loader), loss.item()))
            
            
#定义测试函数
def test(model, device, test_loader):
    model.eval()  #测试模式,不启用BatchNormalization和Dropout
    test_loss = 0
    correct = 0
    with torch.no_grad(): #避免梯度跟踪
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item() #将一批损失相加
            pred = output.max(1, keepdim=True)[1] #找到概率最大的下标
            #上句效果等同于 pred = torch.argmax(output, dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)  
    #len(train_loader)为batch数,len(train_loader.dataset)为样本总数
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.1f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


#开始训练
for epoch in range(1, EPOCHS + 1):
    train(model, DEVICE, train_loader, optimizer, epoch)
    test(model, DEVICE, test_loader)

注意,torch.max()有两种用法:

最终结果如下:

5 小结

  • 任务流程:准备数据,准备模型,训练
  • 如何使用PyTorch自带数据集进行训练
  • 自定义模型需要实现forward函数
  • model.train()和model.eval()作用
  • 最后一层x的交叉熵两种方式等价:CrossEntropyLoss = log_softmax + nll_loss
  • torch.max()有两种用法,返回值不一样

Reference

posted @ 2019-12-30 17:06  天地辽阔  阅读(2490)  评论(0编辑  收藏  举报