使用 AlexNet 实现图片分类

前一篇文章，CNN 卷积神经网络处理图片任务 | PyTorch 深度学习实战

本系列文章 GitHub Repo: https://github.com/hailiang-wang/pytorch-get-started

本篇文章内容来自于强化学习必修课：引领人工智能新时代【梗直哥瞿炜】

经典卷积网络
AlexNet 特点
实验代码
实验结果
Why AlexNet Works
Links

经典卷积网络

以下是卷积神经网络发展的里程碑：

在这里插入图片描述

AlexNet 在各项比赛中，比其它算法好，证明了深度神经网络算法的优越性和前景
VGGNet 则使用比 AlexNet 更深更宽的网络，取得了比 AlexNet 还好的成绩
GoogLeNet 效果则比 VGGNet 更好
ResNet 引入残差模块，解决了深度网络训练中的退化问题，超越之前的模型
DenseNet 模型采用密集连接的结构，使模型具有更好的鲁棒性

AlexNet 特点

在这里插入图片描述

AlexNet 结构

![[../assets/media/screenshot_20250208184431.png]]

更多详细介绍，阅读作者 Paper 论文, ImageNet Classification with Deep Convolutional Neural Networks

视频资源：9年后重读深度学习奠基作之一：AlexNet【上】【论文精读】

实验代码

from torch.utils.data.sampler import SubsetRandomSampler
from torchvision import transforms
from torchvision import datasets
import torch.nn as nn
import torch
import numpy as np

# configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
data_rootdir = os.path.join(os.path.dirname(os.path.abspath(__file__)), os.pardir, "data")


################################
# 定义 dataset loader
################################
def get_train_valid_loader(data_dir,
                           batch_size,
                           augment,
                           random_seed,
                           valid_size=0.1,
                           shuffle=True):

    # 正则化图片的参数，mean 和 std 的值来自于 imagenet 的数据统计
    normalize = transforms.Normalize(
        mean=[0.4914, 0.4822, 0.4465],
        std=[0.2023, 0.1994, 0.2010],
    )

    # define transforms
    valid_transform = transforms.Compose([
        transforms.Resize((227, 227)),
        transforms.ToTensor(),
        normalize,
    ])
    if augment:
        # 数据增强
        train_transform = transforms.Compose([
            transforms.RandomCrop(32, padding=4),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            normalize,
        ])
    else:
        train_transform = transforms.Compose([
            transforms.Resize((227, 227)),
            transforms.ToTensor(),
            normalize,
        ])

    # load the dataset
    train_dataset = datasets.CIFAR10(
        root=data_dir, train=True,
        download=True, transform=train_transform,
    )

    valid_dataset = datasets.CIFAR10(
        root=data_dir, train=True,
        download=True, transform=valid_transform,
    )

    num_train = len(train_dataset)
    indices = list(range(num_train))
    split = int(np.floor(valid_size * num_train))

    if shuffle:
        np.random.seed(random_seed)
        np.random.shuffle(indices)

    train_idx, valid_idx = indices[split:], indices[:split]
    train_sampler = SubsetRandomSampler(train_idx)
    valid_sampler = SubsetRandomSampler(valid_idx)

    train_loader = torch.utils.data.DataLoader(
        train_dataset, batch_size=batch_size, sampler=train_sampler)

    valid_loader = torch.utils.data.DataLoader(
        valid_dataset, batch_size=batch_size, sampler=valid_sampler)

    return (train_loader, valid_loader)


def get_test_loader(data_dir,
                    batch_size,
                    shuffle=True):
    normalize = transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225],
    )

    # define transform
    transform = transforms.Compose([
        transforms.Resize((227, 227)),
        transforms.ToTensor(),
        normalize,
    ])

    dataset = datasets.CIFAR10(
        root=data_dir, train=False,
        download=True, transform=transform,
    )

    data_loader = torch.utils.data.DataLoader(
        dataset, batch_size=batch_size, shuffle=shuffle
    )

    return data_loader


# CIFAR10 dataset
CIFAR10_data = os.path.join(data_rootdir, "CIFAR10")
train_loader, valid_loader = get_train_valid_loader(data_dir= CIFAR10_data,                                      batch_size = 64,
                                                    augment = False,                                          random_seed = 1)

test_loader = get_test_loader(data_dir= CIFAR10_data,
                              batch_size = 64)


################################
# 定义 Model
################################
class AlexNet(nn.Module):
    def __init__(self, num_classes=10):
        super(AlexNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=0),
            nn.BatchNorm2d(96),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 3, stride = 2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(96, 256, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 3, stride = 2))
        self.layer3 = nn.Sequential(
            nn.Conv2d(256, 384, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(384),
            nn.ReLU())
        self.layer4 = nn.Sequential(
            nn.Conv2d(384, 384, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(384),
            nn.ReLU())
        self.layer5 = nn.Sequential(
            nn.Conv2d(384, 256, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 3, stride = 2))
        self.fc = nn.Sequential(
            nn.Dropout(0.5),
            nn.Linear(9216, 4096),
            nn.ReLU())
        self.fc1 = nn.Sequential(
            nn.Dropout(0.5),
            nn.Linear(4096, 4096),
            nn.ReLU())
        self.fc2= nn.Sequential(
            nn.Linear(4096, num_classes))

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.layer5(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        out = self.fc1(out)
        out = self.fc2(out)
        return out

######################################
# Setting Hyperparameters
######################################
num_classes = 10
num_epochs = 20
batch_size = 64
learning_rate = 0.005

model = AlexNet(num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay = 0.005, momentum = 0.9)  

# Train the model
total_step = len(train_loader)


######################################
# Training
######################################
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):  
        # Move tensors to the configured device
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                    .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

    # Validation
    with torch.no_grad():
        correct = 0
        total = 0
        for images, labels in valid_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()
            del images, labels, outputs

        print('Accuracy of the network on the {} validation images: {} %'.format(5000, 100 * correct / total))


# Now, we see how our model performs on unseen data
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()
        del images, labels, outputs

    print('Accuracy of the network on the {} test images: {} %'.format(10000, 100 * correct / total))

在这里插入图片描述