7.2. 使用块的网络（VGG）

Vgg解释

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


def vgg_block(num_convs, in_channels, out_channels):#num_convs重复n次，
    layers = []
    for _ in range(num_convs):#for n次，用_不接收变量 可以节省空间
        layers.append(nn.Conv2d(in_channels, out_channels,kernel_size=3, padding=1))
        layers.append(nn.ReLU())
        in_channels = out_channels
    layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
    return nn.Sequential(*layers)#*layers 数列解包

#为什么5块？ 因为输入224 除2 5次之后是7，没办法再整除   224/2-112/2-56/2-28/2-14/2-7
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))

def vgg(conv_arch):
    conv_blks = []
    in_channels = 1
    # 卷积层部分
    for (num_convs, out_channels) in conv_arch:
        conv_blks.append(vgg_block(num_convs, in_channels, out_channels))
        in_channels = out_channels

    return nn.Sequential(
        *conv_blks, nn.Flatten(),
        # 全连接层部分
        nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(), nn.Dropout(0.5),
        nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),
        nn.Linear(4096, 10))

net = vgg(conv_arch)

X = torch.randn(size=(1, 1, 224, 224))
for blk in net:
    X = blk(X)
    print(blk.__class__.__name__,'output shape:\t',X.shape)


ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
net = vgg(small_conv_arch)

lr, num_epochs, batch_size = 0.05, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

网络添加逻辑：

首先：conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512)) 多个元组做参数

0位置：遍历次数n，1位置：输出通道数

for (num_convs, out_channels) in conv_arch：

第一组（1，64）时，

conv_blks.append(vgg_block(num_convs, in_channels, out_channels))

in_channels = out_channels

 演算后