注：书中对代码的讲解并不详细，本文对很多细节做了详细注释。另外，书上的源代码是在Jupyter Notebook上运行的，较为分散，本文将代码集中起来，并加以完善，全部用vscode在python 3.9.18下测试通过，同时对于书上部分章节也做了整合。

Chapter7 Modern Convolutional Neural Networks

7.1 Deep Convolutional Neural Network: AlexNet

import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt

net = nn.Sequential(
    nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    #使用填充为2来使得输入与输出的高和宽一致，且增大输出通道数
    nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nn.Conv2d(256, 384, kernel_size=3, padding=1), nn.ReLU(),
    nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
    nn.Conv2d(384, 256, kernel_size=3, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nn.Flatten(),
    nn.Linear(6400, 4096), nn.ReLU(),
    nn.Dropout(p=0.5), # 这里全连接层的输出数量是LeNet中的几倍，所以使用dropout层来减轻过拟合
    nn.Linear(4096, 4096), nn.ReLU(),
    nn.Dropout(p=0.5),
    nn.Linear(4096, 10))#由于这里使用Fashion-MNIST，所以用类别数为10，而非论文中的1000

X = torch.randn(1, 1, 224, 224)
for layer in net:
    X=layer(X)
    print(layer.__class__.__name__,'output shape:\t',X.shape)
    
batch_size = 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

#训练
lr, num_epochs = 0.01, 10
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu()) 
plt.show()

训练结果: