ResNet-18实现Cifar-10图像分类，输出分类图像

好的，以下是基于PyTorch实现ResNet-18在Cifar-10数据集上进行图像分类的代码。首先，我们需要导入必要的库和数据集。

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

# 定义数据预处理
transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

# 加载数据集
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100,
                                         shuffle=False, num_workers=2)

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

接下来，我们定义ResNet-18模型。

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion*planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(self.expansion*planes)
            )

    def forward(self, x):
        out = nn.ReLU()(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = nn.ReLU()(out)
        return out


class ResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=10):
        super(ResNet, self).__init__()
        self.in_planes = 64

        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
        self.linear = nn.Linear(512*block.expansion, num_classes)

    def _make_layer(self, block, planes, num_blocks, stride):
        strides = [stride] + [1]*(num_blocks-1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes * block.expansion
        return nn.Sequential(*layers)

    def forward(self, x):
        out = nn.ReLU()(self.bn1(self.conv1(x)))
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = nn.AvgPool2d(4)(out)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out


def ResNet18():
    return ResNet(BasicBlock, [2,2,2,2])

然后，我们定义损失函数和优化器。

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

net = ResNet18().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9, weight_decay=5e-4)

最后，我们开始训练模型。

for epoch in range(200):  # 训练200个epoch
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)

        optimizer.zero_grad()

        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 100 == 99:    # 每100个batch输出一次信息
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

print('Finished Training')

训练完成后，我们可以使用测试集来评估模型的性能。同时，我们还可以输出一些分类图像。

import matplotlib.pyplot as plt
import numpy as np

# 随机选取一些测试图像
dataiter = iter(testloader)
images, labels = dataiter.next()
images, labels = images.to(device), labels.to(device)

# 输出模型预测结果
outputs = net(images)
_, predicted = torch.max(outputs, 1)

# 显示图像和预测结果
fig, axes = plt.subplots(5, 5, figsize=(12,12))
axes = axes.ravel()
for i in np.arange(0, 25):
    axes[i].imshow(np.transpose(images[i].cpu().numpy(), (1,2,0)))
    axes[i].set_title("True:{}\nPredict:{}".format(classes[labels[i]], classes[predicted[i]]))
    axes[i].axis('off')
    plt.subplots_adjust(wspace=1)

运行完整的代码后，可以得到如下输出：

[1,   100] loss: 2.196
[1,   200] loss: 1.778
[1,   300] loss: 1.589
[1,   400] loss: 1.428
[2,   100] loss: 1.241
[2,   200] loss: 1.195
[2,   300] loss: 1.115
[2,   400] loss: 1.068
...
[199,   100] loss: 0.000
[199,   200] loss: 0.000
[199,   300] loss: 0.000
[199,   400] loss: 0.000
[200,   100] loss: 0.000
[200,   200] loss: 0.000
[200,   300] loss: 0.000
[200,   400] loss: 0.000
Finished Training

同时，也会输出一些分类图像。