import torch
from torch import nn
net = nn.Sequential(
# 这里,我们使用一个11*11的更大窗口来捕捉对象。
# 同时,步幅为4,以减少输出的高度和宽度。
# 另外,输出通道的数目远大于LeNet
nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
# 减小卷积窗口,使用填充为2来使得输入与输出的高和宽一致,且增大输出通道数
nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
# 使用三个连续的卷积层和较小的卷积窗口。
# 除了最后的卷积层,输出通道的数量进一步增加。
# 在前两个卷积层之后,汇聚层不用于减少输入的高度和宽度
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.Conv2d(256, 256, kernel_size=3, padding=1), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Flatten(),
# 这里,全连接层的输出数量是LeNet中的好几倍。使用dropout层来减轻过拟合
nn.Dropout(p=0.5),
nn.Linear(256*6*6, 4096), nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(4096, 4096), nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(4096, 1000))
使用更小的卷积核
小卷积核探测面积小,大卷积核探测面积大。使用2个3 * 3卷积核的“探测”面积等价于1一个5 * 5卷积核的“探测”面积;使用3个3 * 3卷积核的“探测”面积等价于1一个7 * 7卷积核的“探测”面积。
小卷积核堆叠使用更少的参数;小卷积核堆叠使用更少的计算量;小卷积核堆叠的非线性表达能力更强。
更深的模型
原始VGG网络有5个卷积块,其中前两个块各有一个卷积层,后三个块各包含两个卷积层。 第一个模块有64个输出通道,每个后续模块将输出通道数量翻倍,直到该数字达到512。由于该网络使用8个卷积层和3个全连接层,因此它通常被称为VGG-11。
def vgg_block(num_convs, in_channels, out_channels):
layers = []
for _ in range(num_convs):
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)
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)
def nin_block(in_channels, out_channels, kernel_size, strides, padding):
return nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size, strides, 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())
net = nn.Sequential(
nin_block(1, 96, kernel_size=11, strides=4, padding=0),
nn.MaxPool2d(3, stride=2),
nin_block(96, 256, kernel_size=5, strides=1, padding=2),
nn.MaxPool2d(3, stride=2),
nin_block(256, 384, kernel_size=3, strides=1, padding=1),
nn.MaxPool2d(3, stride=2),
nn.Dropout(0.5),
# 标签类别数是10
nin_block(384, 10, kernel_size=3, strides=1, padding=1),
nn.AdaptiveAvgPool2d((1, 1)),
# 将四维的输出转成二维的输出,其形状为(批量大小,10)
nn.Flatten())
并联执行小规模的卷积池化,使得卷积结构变得更加稀疏;
卷积采用不同大小的卷积核,可提取不同尺度上的特征;
并联的卷积与池化得到的特征图再通道上进行拼接,使得后面的层能够利用前面提取到的多尺度特征;
合并通道带来维度灾难问题,尤其是池化层。
使用 1 * 1 卷积降低了模型参数规模;
使用 1 * 1 卷积降低了通道规模;
两次卷积提高了Inception模块的非线性拟合能力
class Inception(nn.Module):
# c1--c4是每条路径的输出通道数
def __init__(self, in_channels, c1, c2, c3, c4, **kwargs):
super(Inception, self).__init__(**kwargs)
# 线路1,单1x1卷积层
self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
# 线路2,1x1卷积层后接3x3卷积层
self.p2_1 = nn.Conv2d(in_channels, c2[0], kernel_size=1)
self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
# 线路3,1x1卷积层后接5x5卷积层
self.p3_1 = nn.Conv2d(in_channels, c3[0], kernel_size=1)
self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
# 线路4,3x3最大汇聚层后接1x1卷积层
self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
self.p4_2 = nn.Conv2d(in_channels, 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)))
# 在通道维度上连结输出
return torch.cat((p1, p2, p3, p4), dim=1)
import torch
from torch import nn
from torch.nn import functional as F
class Residual(nn.Module): #@save
def __init__(self, input_channels, num_channels,
use_1x1conv=False, strides=1):
super().__init__()
self.conv1 = nn.Conv2d(input_channels, num_channels,
kernel_size=3, padding=1, stride=strides)
self.conv2 = nn.Conv2d(num_channels, num_channels,
kernel_size=3, padding=1)
if use_1x1conv:
self.conv3 = nn.Conv2d(input_channels, num_channels,
kernel_size=1, stride=strides)
else:
self.conv3 = None
self.bn1 = nn.BatchNorm2d(num_channels)
self.bn2 = nn.BatchNorm2d(num_channels)
def forward(self, X):
Y = F.relu(self.bn1(self.conv1(X)))
Y = self.bn2(self.conv2(Y))
if self.conv3:
X = self.conv3(X)
Y += X
return F.relu(Y)
#残差快
def resnet_block(input_channels, num_channels, num_residuals,
first_block=False):
blk = []
for i in range(num_residuals):
if i == 0 and not first_block:
blk.append(Residual(input_channels, num_channels,
use_1x1conv=True, strides=2))
else:
blk.append(Residual(num_channels, num_channels))
return blk
#ResNet的前两层跟之前介绍的GoogLeNet中的一样: 在输出通道数为64、步幅为2的 7×7 卷积层后,接步幅为2的 3×3 的最大汇聚层。 不同之处在于ResNet每个卷积层后增加了批量规范化层。
b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
nn.BatchNorm2d(64), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
# ResNet则使用4个由残差块组成的模块,每个模块使用若干个同样输出通道数的残差块。 第一个模块的通道数同输入通道数一致
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))
#在ResNet中加入全局平均汇聚层,以及全连接层输出
net = nn.Sequential(b1, b2, b3, b4, b5,
nn.AdaptiveAvgPool2d((1,1)),
nn.Flatten(), nn.Linear(512, 10))