P4：猴痘病识别

>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

🏡我的环境：

语言环境: Python 3.11.7
编译器：Pycharm
深度学习环境：
torch==1.12.1+cu113
torchvision==0.13.1+cu113

一、 前期准备

1. 设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import pathlib
import numpy as np
from pathlib import Path

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

2. 导入数据

data_dir = './4-data/'
data_paths = list(data_dir.glob('*'))
classNames = [path.name for path in data_paths]
total_datadir = './4-data/'
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),
    transforms.ToTensor(),
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225]
    )
])

total_data = datasets.ImageFolder(total_datadir, transform=train_transforms)

3. 划分数据集

train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])

batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=1)
for X, y in test_dl:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

二、构建简单的CNN网络

import torch.nn.functional as F

class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2,2)
        self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn5 = nn.BatchNorm2d(24)
        self.fc1 = nn.Linear(24*50*50, len(classNames))

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))
        x = F.relu(self.bn2(self.conv2(x)))
        x = self.pool(x)
        x = F.relu(self.bn4(self.conv4(x)))
        x = F.relu(self.bn5(self.conv5(x)))
        x = self.pool(x)
        x = x.view(-1, 24*50*50)
        x = self.fc1(x)

        return x

device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = Network_bn().to(device)

三、 训练模型

1. 设置超参数

loss_fn    = nn.CrossEntropyLoss()
learn_rate = 1e-4
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2. 编写训练函数

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    num_batches = int(np.ceil(len(dataloader.dataset) / dataloader.batch_size))
    train_loss, train_acc = 0, 0

    for X, y in dataloader:
        X, y = X.to(device), y.to(device)

        pred = model(X)
        loss = loss_fn(pred, y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()

    train_acc /= size
    train_loss /= num_batches

    return train_acc, train_loss

3. 编写测试函数

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = int(np.ceil(len(dataloader.dataset) / dataloader.batch_size))
    test_loss, test_acc = 0, 0

    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)

            pred = model(X)
            loss = loss_fn(pred, y)

            test_loss += loss.item()
            test_acc += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_acc /= size
    test_loss /= num_batches

    return test_acc, test_loss

4. 正式训练

epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)

    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)

    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)

    print(f'Epoch {epoch+1}/{epochs}, Train Acc: {epoch_train_acc:.4f}, Train Loss: {epoch_train_loss:.4f}, Test Acc: {epoch_test_acc:.4f}, Test Loss: {epoch_test_loss:.4f}')

print('Done')

四、 结果可视化

import matplotlib.pyplot as plt

plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
plt.plot(range(1, epochs+1), train_acc, label='Training Accuracy')
plt.plot(range(1, epochs+1), test_acc, label='Validation Accuracy')
plt.legend()
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(range(1, epochs+1), train_loss, label='Training Loss')
plt.plot(range(1, epochs+1), test_loss, label='Validation Loss')
plt.legend()
plt.title('Training and Validation Loss')

plt.show()

了解到如何使用PyTorch进行图像分类任务的典型流程，包括数据预处理、模型定义、训练和测试等步骤。此外，还学习了如何使用批归一化和交叉熵损失函数来提高模型的性能。