机器学习练手项目-猫狗分类器

GeekLiHua

发布于 2025-01-21 16:46:01

3300

代码可运行

文章被收录于专栏：JavaJava

运行总次数：0

代码可运行

机器学习练手项目-猫狗分类器

猫狗分类器是一个深度学习项目，旨在识别图像中的猫和狗。通过训练神经网络模型，该项目可以从输入的图像中准确地识别出是猫还是狗。这个项目可以应用于许多实际场景，如图像分类、动物识别等。

1. 准备数据集

首先，需要准备一个包含猫和狗图像的数据集。您可以从各种来源收集这些图像数据，例如网络上的图片库或自己的图片文件夹。确保每个类别的图像都放在单独的文件夹中，并将它们命名为相应的类别。

2. 数据预处理

在加载图像数据之前，需要进行一些预处理步骤。这包括调整图像大小、将图像转换为张量以及标准化图像数据。通过torchvision.transforms模块，我们可以方便地实现这些预处理步骤。

import torch
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader

3. 构建模型

将使用卷积神经网络（CNN）来构建我们的猫狗分类器。CNN是一种在图像识别任务中非常流行的深度学习模型。

import torch.nn as nn
import torch.nn.functional as F

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        # 定义卷积层、池化层和全连接层
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
        self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 8 * 8, 512)
        self.fc2 = nn.Linear(512, 2)

    def forward(self, x):
        # 前向传播函数
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.pool(F.relu(self.conv3(x)))
        x = x.view(-1, 64 * 8 * 8)  # 将特征展平为一维向量
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

4. 训练模型

将使用训练集来训练我们的模型，并使用测试集来评估模型的性能。

import torch.optim as optim

# 实例化模型、定义损失函数和优化器
model = CNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 10
for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        try:
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item()
            if (i+1) % 100 == 0:
                print(f'Epoch [{epoch+1}/{num_epochs}], Iteration [{i+1}/{len(train_loader)}], Loss: {running_loss/100:.4f}')
                running_loss = 0.0
        except Exception as e:
            print(f"Error processing batch {i}:", str(e))
            continue

print('Finished Training')

5. 评估模型

在训练完成后，需要评估模型在测试集上的性能。

model.eval()
correct = 0
total = 0
with torch.no_grad():
    for data in test_loader:
        images, labels = data
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f'Accuracy of the network on the {total} test images: {100 * correct / total}%')

完整代码：

import os
import torch
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import matplotlib.pyplot as plt
from PIL import Image

# 设置随机种子
torch.manual_seed(42)

# 数据预处理，包括调整大小、转换为张量、以及标准化
transform = transforms.Compose([
    transforms.Resize((64, 64)),  # 将图像调整为 64x64 大小
    transforms.ToTensor(),         # 将图像转换为张量
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])  # 标准化图像数据
])

# 加载训练数据集，使用ImageFolder自动加载图像数据，并应用上面定义的数据预处理
# root参数指定数据集根目录
train_dataset = ImageFolder(root='D:\\系统默认\\桌面\\python\\PetImages\\', transform=transform)

# 计算训练集的大小
train_size = int(0.8 * len(train_dataset))
test_size = len(train_dataset) - train_size

# 划分训练集和测试集
train_dataset, test_dataset = torch.utils.data.random_split(train_dataset, [train_size, test_size])

# 创建数据加载器，用于加载训练集和测试集的数据
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=4, shuffle=False)

# 定义卷积神经网络模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        # 定义卷积层
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
        self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
        # 定义池化层
        self.pool = nn.MaxPool2d(2, 2)
        # 定义全连接层
        self.fc1 = nn.Linear(64 * 8 * 8, 512)
        self.fc2 = nn.Linear(512, 2)

    def forward(self, x):
        # 前向传播函数，定义网络结构
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.pool(F.relu(self.conv3(x)))
        x = x.view(-1, 64 * 8 * 8)  # 将特征展平为一维向量
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 实例化模型、定义损失函数和优化器
model = CNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 10
for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        try:
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item()
            if (i+1) % 100 == 0:
                print(f'Epoch [{epoch+1}/{num_epochs}], Iteration [{i+1}/{len(train_loader)}], Loss: {running_loss/100:.4f}')
                running_loss = 0.0
        except Exception as e:
            print(f"Error processing batch {i}:", str(e))
            continue

print('Finished Training')

# 保存模型
torch.save(model.state_dict(), 'cat_dog_model.pth')

# 测试模型
model.eval()
correct = 0
total = 0
with torch.no_grad():
    for data in test_loader:
        images, labels = data
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f'Accuracy of the network on the {total} test images: {100 * correct / total}%')