VGG网络

VGG这个名字来源于论文作者所在的实验室Visual Geometry Group。其提出了可以通过重复使用简单的基础块来构建深度模型的思路。

VGG块（VGG-block）的结构：

1.单层或者多层的卷积层

2.单层池化层

import d2lzh as d2l
from mxnet import gluon, init, nd
from mxnet.gluon import nn

def vgg_block(num_convs, num_channels):
    blk = nn.Sequential()
    for _ in range(num_convs):
        blk.add(nn.Conv2D(num_channels, kernel_size=3,
                          padding=1, activation='relu'))
    blk.add(nn.MaxPool2D(pool_size=2, strides=2))
    return blk

VGG网络：

与AlexNet与LeNet一样，VGG网络由卷积层模块后接全连接层模块构成。卷积层模块串联数个vgg_block构成，其超参数由变量conv_arch定义，该变量指定了每个VGG块里卷积层个数和输出通道数。全连接模块则是由丢弃法的模块。

# 包含了5个vgg-block，总共8个卷积层，通道数慢慢增加到从64慢慢增加到512
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))

# 使用了8个卷积层和3个全连接层，所以被称为VGG-11
def vgg(conv_arch):
    net = nn.Sequential()
    # 卷积层部分
    for (num_convs, num_channels) in conv_arch:
        net.add(vgg_block(num_convs, num_channels))
    # 全连接层部分
    net.add(nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
            nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
            nn.Dense(10))
    return net

net = vgg(conv_arch)

训练：

# 处于测试目的，将VGG网络的通道数缩小
ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
net = vgg(small_conv_arch)

# 训练
lr, num_epochs, batch_size, ctx = 0.05, 5, 128, d2l.try_gpu()
net.initialize(ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx,
              num_epochs)

参考文献：

动手学深度学习——阿斯顿张、李沐