Pytorch实现猫狗分类

在进行编码之前，确保已经安装好Pytorch以及相关依赖环境

模型定义构建

构建一个较为简单的卷积神经网络模型

# 定义神经网络模型
class CatDogClassifier(nn.Module):
    def __init__(self):
        super(CatDogClassifier, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=5, stride=1, padding=2)
        self.relu = nn.ReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2)
        self.fc = nn.Linear(32 * 56 * 56, 2)

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.maxpool(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.maxpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

加载数据并进行预处理

注意将代码中的路径替换为自己的数据集所在的文件路径。
Normalize部分的参数可以自行调整，或者搜索一个合理的参数设定。

transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

train_dataset = torchvision.datasets.ImageFolder(root='path_to_training_data', transform=transform)
test_dataset = torchvision.datasets.ImageFolder(root='path_to_test_data', transform=transform)

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=32, shuffle=False)

初始化模型、优化器等

lr设定为0.001，可以自行调整设置。

model = CatDogClassifier()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

训练模型

num_epochs = 10
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)

for epoch in range(num_epochs):
    for images, labels in train_loader:
        images = images.to(device)
        labels = labels.to(device)

        # 前向传播
        outputs = model(images)
        loss = criterion(outputs, labels)

        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item()}')

测试模型

在训练和测试模型时，注意使用eval()进行模式切换。

model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)

        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    accuracy = 100 * correct / total
    print(f'Test Accuracy: {accuracy}%')

完整代码

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

# 定义神经网络模型
class CatDogClassifier(nn.Module):
    def __init__(self):
        super(CatDogClassifier, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=5, stride=1, padding=2)
        self.relu = nn.ReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2)
        self.fc = nn.Linear(32 * 56 * 56, 2)

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.maxpool(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.maxpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

# 加载并预处理数据
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

train_dataset = torchvision.datasets.ImageFolder(root='path_to_training_data', transform=transform)
test_dataset = torchvision.datasets.ImageFolder(root='path_to_test_data', transform=transform)

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=32, shuffle=False)

# 初始化模型和优化器
model = CatDogClassifier()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 10
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)

for epoch in range(num_epochs):
    for images, labels in train_loader:
        images = images.to(device)
        labels = labels.to(device)

        # 前向传播
        outputs = model(images)
        loss = criterion(outputs, labels)

        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item()}')

# 测试模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)

        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    accuracy = 100 * correct / total
    print(f'Test Accuracy: {accuracy}%')