LeNet、AlexNet和VGG都是不断的加深模型的层数,看网络结构可以看出后者有前者的影子,并且都是一系列卷积+最后全连接的操作。
NiN却是网络串联网络,并且NiN最后的分类方法也很不同。
之前的网络都是卷积提取特征之后带全连接做分类。NiN提供另一个思路,卷积层和全连接层交替。因为全连接层的输入输出要是二维,卷积通常是四维,为了方便全连接层使用1 × \times × 1 卷积代替。原理之前解释过。
贡献:
import torch
from torch import nn
import torch.nn.functional as F
import d2l as d2l
def nin_block(in_channels, out_channels, kernel_size, stride, padding):
blk = nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding),
nn.ReLU(),
nn.Conv2d(out_channels, out_channels, kernel_size=1),
nn.ReLU(),
nn.Conv2d(out_channels, out_channels, kernel_size=1),
nn.ReLU())
return blk
net = nn.Sequential(
nin_block(1, 96, kernel_size=11, stride=4, padding=0),
nn.MaxPool2d(kernel_size=3, stride=2),
nin_block(96, 256, kernel_size=5, stride=1, padding=2),
nn.MaxPool2d(kernel_size=3, stride=2),
nin_block(256, 384, kernel_size=3, stride=1, padding=1),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Dropout(0.5),
# 标签类别数是10
nin_block(384, 10, kernel_size=3, stride=1, padding=1),
d2l.GlobalAvgPool2d(), # 全局平均池化
# 将四维的输出转成二维的输出,其形状为(批量大小, 10)
d2l.FlattenLayer()
)
改进很大,除了吸收了NiN的串联网路的思想,设置的基础模块也更加复杂。它认为之前加深层数会导致参数太多、计算复杂难以应用、出现梯度消失的问题。要解决这个问题不得不引入稀疏性并且把全连接变为稀疏连接。
引入稀疏性可以从下面两个方面着手:
参考:https://blog.csdn.net/weixin_43624538/article/details/84863685
https://blog.csdn.net/weixin_30888027/article/details/97739699
https://www.cnblogs.com/leebxo/p/10315490.html
import torch
from torch import nn
import torch.nn.functional as F
import d2l as d2l
class Inception(nn.Module):
# c1 - c4为每条线路里的层的输出通道数
def __init__(self, in_c, c1, c2, c3, c4):
super(Inception, self).__init__()
# 线路1,单1 x 1卷积层
self.p1_1 = nn.Conv2d(in_c, c1, kernel_size=1)
# 线路2,1 x 1卷积层后接3 x 3卷积层
self.p2_1 = nn.Conv2d(in_c, c2[0], kernel_size=1)
self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
# 线路3,1 x 1卷积层后接5 x 5卷积层
self.p3_1 = nn.Conv2d(in_c, c3[0], kernel_size=1)
self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
# 线路4,3 x 3最大池化层后接1 x 1卷积层
self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
self.p4_2 = nn.Conv2d(in_c, c4, kernel_size=1)
def forward(self, x):
p1 = F.relu(self.p1_1(x))
p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
p4 = F.relu(self.p4_2(self.p4_1(x)))
return torch.cat((p1, p2, p3, p4), dim=1) # 在通道维上连结输出
b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1),
nn.Conv2d(64, 192, kernel_size=3, padding=1),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
Inception(256, 128, (128, 192), (32, 96), 64),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
Inception(512, 160, (112, 224), (24, 64), 64),
Inception(512, 128, (128, 256), (24, 64), 64),
Inception(512, 112, (144, 288), (32, 64), 64),
Inception(528, 256, (160, 320), (32, 128), 128),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
Inception(832, 384, (192, 384), (48, 128), 128),
d2l.GlobalAvgPool2d())
net = nn.Sequential(b1, b2, b3, b4, b5,
d2l.FlattenLayer(), nn.Linear(1024, 10))