AlexNet网络

AlexNet

改进（基于LeNet）

1. 采用ReLU激活函数（解决了梯度消失问题）
2. 丢弃法
3. MaxPooling
4. 数据增强

网络结构

和LeNet相比，网络结构更复杂，层和核更大

代码

import torch
from torch import nn
from d2l import torch as d2l

net = nn.Sequential(
    #卷积单元
    nn.Conv2d(1,96,kernel_size=11,stride=4, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    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),
    #全连接单元
    nn.Flatten(),
    nn.Linear(6400, 4096), nn.ReLU(),
    nn.Dropout(0.5),     #丢弃层
    nn.Linear(4096, 4096), nn.ReLU(),   
    nn.Dropout(0.5),
    nn.Linear(4096, 10)
)

# X = torch.randn(1, 1, 224, 224)  # 输入图像的形状
# for layer in net:
#     X = layer(X)  # 前向传播
#     print(layer.__class__.__name__, 'output shape:\t', X.shape)

if __name__ == "__main__":
    batch_size = 128
    train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
    lr, num_epochs = 0.01, 10
    d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())