P2：CIFAR10彩色图片识别

>- **🍨 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 os
import torch
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
import torchvision
from torchinfo import summary  # Importing summary function

os.environ['OMP_NUM_THREADS'] = '1'
os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'

# 设置使用的设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

2. 导入数据

train_ds = torchvision.datasets.CIFAR10('data',
                                         train=True,
                                         transform=torchvision.transforms.ToTensor(),  # 将数据类型转化为Tensor
                                         download=True)

test_ds = torchvision.datasets.CIFAR10('data',
                                        train=False,
                                        transform=torchvision.transforms.ToTensor(),  # 将数据类型转化为Tensor
                                        download=True)
batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds,
                                       batch_size=batch_size,
                                       shuffle=True)

test_dl = torch.utils.data.DataLoader(test_ds,
                                      batch_size=batch_size)
imgs, labels = next(iter(train_dl))
print(imgs.shape)

3. 数据可视化

import numpy as np

# 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5))
for i, imgs in enumerate(imgs[:20]):
    # 维度缩减
    npimg = imgs.numpy().transpose((1, 2, 0))
    # 将整个figure分成2行10列，绘制第i+1个子图。
    plt.subplot(2, 10, i + 1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')

plt.show()

二、构建简单的CNN网络

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        # 特征提取网络
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3)  # 第一层卷积,卷积核大小为3*3
        self.pool1 = nn.MaxPool2d(kernel_size=2)  # 设置池化层，池化核大小为2*2
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3)  # 第二层卷积,卷积核大小为3*3
        self.pool2 = nn.MaxPool2d(kernel_size=2)
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3)  # 第二层卷积,卷积核大小为3*3
        self.pool3 = nn.MaxPool2d(kernel_size=2)

        # 分类网络
        self.fc1 = nn.Linear(128 * 2 * 2, 256)  # Update the input size for the fully connected layer
        self.fc2 = nn.Linear(256, num_classes)

    # 前向传播
    def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))
        x = self.pool3(F.relu(self.conv3(x)))

        x = torch.flatten(x, start_dim=1)

        x = F.relu(self.fc1(x))
        x = self.fc2(x)

        return x


# 实例化模型
model = Model().to(device)

# 打印模型信息
summary(model, input_size=(batch_size, 3, 32, 32))

三、 训练模型

1. 设置超参数

loss_fn = nn.CrossEntropyLoss()  # 创建损失函数
learn_rate = 1e-2  # 学习率
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)  # 训练集的大小，一共60000张图片
    num_batches = len(dataloader)  # 批次数目，1875（60000/32）

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率

    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)

        # 计算预测误差
        pred = model(X)  # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失

        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()  # 反向传播
        optimizer.step()  # 每一步自动更新

        # 记录acc与loss
        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)  # 测试集的大小，一共10000张图片
    num_batches = len(dataloader)  # 批次数目，313（10000/32=312.5，向上取整）
    test_loss, test_acc = 0, 0

    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)

            # 计算loss
            target_pred = model(imgs)
            loss = loss_fn(target_pred, target)

            test_loss += loss.item()
            test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc /= size
    test_loss /= num_batches

    return test_acc, test_loss

4. 正式训练

# 模型训练参数
epochs = 10
train_accuracy = []
train_loss = []
test_accuracy = []
test_loss = []

# 训练模型
for epoch in range(epochs):
    # 模型训练
    model.train()
    acc, loss = train(train_dl, model, loss_fn, opt)
    train_accuracy.append(acc)
    train_loss.append(loss)

    # 模型测试
    model.eval()
    acc, loss = test(test_dl, model, loss_fn)
    test_accuracy.append(acc)
    test_loss.append(loss)

    # 打印每个epoch的训练结果
    print(f"Epoch {epoch + 1}: Train Accuracy: {train_accuracy[-1]:.4f}, Train Loss: {train_loss[-1]:.4f}, "
          f"Test Accuracy: {test_accuracy[-1]:.4f}, Test Loss: {test_loss[-1]:.4f}")
print('Done')

四、 结果可视化

# 绘制训练过程中的准确率和损失变化
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
plt.plot(range(1, epochs + 1), train_accuracy, label='Train Accuracy')
plt.plot(range(1, epochs + 1), test_accuracy, label='Test Accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.title('Training and Testing Accuracy')
plt.legend()
plt.subplot(1, 2, 2)
plt.plot(range(1, epochs + 1), train_loss, label='Train Loss')
plt.plot(range(1, epochs + 1), test_loss, label='Test Loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.title('Training and Testing Loss')
plt.legend()
plt.show()

• 总结：学会使用部分函数，还需对神经网络进行进一步的理解与学习。