VGG使用块的网络

VGG使用块的网络

一.手写VGG架构

import torch
from torch import nn
import d2l
#1.VGG块
def VGG_block(nums_conv,in_chanels,out_chanels):#卷积层数，输入通道数，输出通道数
    layers=[]#一个VGG里面的层
    for i in range(nums_conv):
        layers.append(
            nn.Conv2d(in_chanels,out_chanels,3,padding=1)
        )
        layers.append(
            nn.ReLU()
        )
        in_chanels=out_chanels#下一层输入等于本层输出
    layers.append(
        nn.MaxPool2d(kernel_size=2,stride=2)
    )
    return nn.Sequential(*layers)
#VGG网络由多个VGG块组成
def VGG_net(conv_info):#传入有关每一个块的卷积情况
    conv_blocks=[]
    in_chanels=1#默认输入通道初始是1
    for (nums_conv,out_chanels) in conv_info:
        conv_blocks.append(VGG_block(nums_conv,in_chanels,out_chanels))
        in_chanels=out_chanels#下一层输入等于本层输出
    return nn.Sequential(
        *conv_blocks,nn.Flatten(),
        nn.Linear(7*7*out_chanels,4096),
        nn.ReLU(),
        nn.Dropout(p=0.5),
        nn.Linear(4096,4096),
        nn.ReLU(),
        nn.Dropout(p=0.5),
        nn.Linear(4096,10)
    )
conv_info=((1,64),(1,128),(2,256),(2,512),(2,512))
net=VGG_net(conv_info)
X=torch.randn((1,1,224,224))
for layer in net:
    X=layer(X)
    print(layer.__class__.__name__,X.shape)

分析代码：

VGG网络架构，由多个VGG块以及3个全连接层组成

每个VGG块可以不同，VGG块由多个3*3padding=1的卷积层和一个2*2stride=2的最大池化层组成

（1）VGG块

def VGG_block(nums_conv,in_chanels,out_chanels):#卷积层数，输入通道数，输出通道数
    layers=[]#一个VGG里面的层
    for i in range(nums_conv):
        layers.append(
            nn.Conv2d(in_chanels,out_chanels,3,padding=1)
        )
        layers.append(
            nn.ReLU()
        )
        in_chanels=out_chanels#下一层输入等于本层输出
    layers.append(
        nn.MaxPool2d(kernel_size=2,stride=2)
    )
    return nn.Sequential(*layers)

 （2）VGG网络

def VGG_net(conv_info):#传入有关每一个块的卷积情况
    conv_blocks=[]
    in_chanels=1#默认输入通道初始是1
    for (nums_conv,out_chanels) in conv_info:
        conv_blocks.append(VGG_block(nums_conv,in_chanels,out_chanels))
        in_chanels=out_chanels#下一层输入等于本层输出
    return nn.Sequential(#这一部分和AlexNet一样，三层全连接层
        *conv_blocks,nn.Flatten(),
        nn.Linear(7*7*out_chanels,4096),
        nn.ReLU(),
        nn.Dropout(p=0.5),
        nn.Linear(4096,4096),
        nn.ReLU(),
        nn.Dropout(p=0.5),
        nn.Linear(4096,10)
    )

---

二.训练VGG网络 

import torch
from torch import nn
from d2l import torch as d2l
#1.VGG块
def VGG_block(nums_conv,in_chanels,out_chanels):#卷积层数，输入通道数，输出通道数
    layers=[]#一个VGG里面的层
    for i in range(nums_conv):
        layers.append(
            nn.Conv2d(in_chanels,out_chanels,3,padding=1)
        )
        layers.append(
            nn.ReLU()
        )
        in_chanels=out_chanels#下一层输入等于本层输出
    layers.append(
        nn.MaxPool2d(kernel_size=2,stride=2)
    )
    return nn.Sequential(*layers)

#VGG网络由多个VGG块组成
def VGG_net(conv_info):#传入有关每一个块的卷积情况
    conv_blocks=[]
    in_chanels=1#默认输入通道初始是1
    for (nums_conv,out_chanels) in conv_info:
        conv_blocks.append(VGG_block(nums_conv,in_chanels,out_chanels))
        in_chanels=out_chanels#下一层输入等于本层输出
    nn.Flatten()
    return nn.Sequential(
        *conv_blocks,nn.Flatten(),
        nn.Linear(7*7*out_chanels,4096),
        nn.ReLU(),
        nn.Dropout(p=0.5),
        nn.Linear(4096,4096),
        nn.ReLU(),
        nn.Dropout(p=0.5),
        nn.Linear(4096,10)
    )
conv_info=((1,64),(1,128),(2,256),(2,512),(2,512))
#因为这个VGG网络层数太多运行太慢，所以把输出通道除4
ratio=4
smallconv_info=[(pair[0],pair[1]//ratio) for pair in conv_info]
net=VGG_net(smallconv_info)
batch_size=128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size=batch_size,resize=224)#数据集
lr=0.05
nums_epochs=10
d2l.train_ch6(net,train_iter,test_iter,nums_epochs,lr,d2l.try_gpu())