pytorch：对CIFAR10图片进行分类-优快云博客

本文链接：https://blog.youkuaiyun.com/z2536083458/article/details/89058472

本文介绍了一个基于PyTorch实现的CIFAR-10数据集上的图片分类项目，包括数据加载与预处理、卷积神经网络的设计、损失函数与优化器的选择、模型训练及最终在测试集上的效果评估。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

参考资料：https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py

图片分类模型的具体步骤：

加载数据，对数据进行归一化处理（使用torchvision）
定义卷积神经网络
定义损失函数
在训练集上训练神经网络
在测试集上进行测试

import torch
import torchvision
import torchvision.transforms as transforms

1.加载数据

# 1.加载数据
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

显示图片

import matplotlib.pyplot as plt
import numpy as np

def imshow(img):
    img = img / 2 + 0.5
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()
    
dataiter = iter(trainloader)
images, labels = dataiter.next()
imshow(torchvision.utils.make_grid(images))
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
# car dog car truck

在这里插入图片描述

2.定义卷积神经网络

# 2.定义卷积神经网络
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
        
net = Net()

3. 定义损失函数和优化器

# 3.定义损失函数和优化器
import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

4.训练网络

# 4.训练网络结构
for epoch in range(2):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
        if i % 2000 == 1999:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0
            
print('Finished Training')

5.在测试集上进行测试

# 5.在测试集上进行测试
dataiter = iter(testloader)
images, labels = dataiter.next()

imshow(torchvision.utils.make_grid(images))
print('GroundTruth:', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
# cat ship ship plane