卷积神经网络学习笔记-分类网络（一）
目录
1.1 Alexnet
1.2Alexnet构建
2.1VggNet
2.2VggNet构建
3.1GoogleNet
3.2GoogleNet构建
4 、引用
1.1 Alexnet
网络亮点是基于ImageNet数据集的卷积神经网络，比起其他模型，卷积神经网络的分类错误指标明显减少。
1.使用了多块GPU进行加速
2.在全连接前两层使用了dropout随机失活的技术，减少过拟合
其结构如下图所示：
1.2Alexnet构建
import torch.nn as nn
import torch
class AlexNet(nn.Module):
def __init__(self, num_classes=1000, init_weights=False):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2), # input[3, 224, 224] output[96, 55, 55]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[96, 27, 27]
nn.Conv2d(96, 128, kernel_size=5, padding=2), # output[128, 27, 27]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 13, 13]
nn.Conv2d(128, 192, kernel_size=3, padding=1), # output[192, 13, 13]
nn.ReLU(inplace=True),
nn.Conv2d(192, 192, kernel_size=3, padding=1), # output[192, 13, 13]
nn.ReLU(inplace=True),
nn.Conv2d(192, 128, kernel_size=3, padding=1), # output[128, 13, 13]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 6, 6]
)
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(128 * 6 * 6, 2048),
nn.ReLU(inplace=True),
nn.Dropout(p=0.5),
nn.Linear(2048, 2048),
nn.ReLU(inplace=True),
nn.Linear(2048, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
def _initialize_weights(self):#权值初始化
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)2.1VggNet
网络中的亮点是通过堆叠多个3×3的卷积核来代替大尺度卷积核，减少所需参数。论文提到堆叠两个3×3的卷积核可以代替一个5×5的卷积核，堆叠三个3×3的卷积核可以代替一个7×7的卷积核。其拥有相同的感受野。
感受野简单来说就是输出的特征矩阵一个单元对应这输入层的区域大小。感受野计算公式如下，那么三个3×3的卷积核堆叠，第三层一个1×1单位对应的第一层感受野是7×7。
网络结构如下图，最常用的为D模型，Vgg16，通过两个3×3的卷积核->最大下采样->两个3×3的卷积核->最大下采样 ->三个3×3卷积核->最大下采样->三个3×3卷积核->最大下采样->三个3×3卷积核->最大下采样->三个全连接层->softmax。卷积的stride=1，padding=1,maxpool的stride=2，size=2。
2.2VggNet构建
import torch.nn as nn
import torch
# official pretrain weights预训练权重
model_urls = {
'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth'
}
class VGG(nn.Module):
def __init__(self, features, num_classes=1000, init_weights=False):
super(VGG, self).__init__()
self.features = features
self.classifier = nn.Sequential(
nn.Linear(512*7*7, 4096),
nn.ReLU(True),
nn.Dropout(p=0.5),#随即失活
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(p=0.5),
nn.Linear(4096, num_classes)
)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N x 3 x 224 x 224
x = self.features(x)
# N x 512 x 7 x 7
x = torch.flatten(x, start_dim=1)#channel维度展平
# N x 512*7*7
x = self.classifier(x)
return x
def _initialize_weights(self):#权重初始化
for m in self.modules():
if isinstance(m, nn.Conv2d):
# nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
nn.init.xavier_uniform_(m.weight)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.xavier_uniform_(m.weight)
# nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
def make_features(cfg: list):
layers = []
in_channels = 3
for v in cfg:
if v == "M":
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
layers += [conv2d, nn.ReLU(True)]
in_channels = v
return nn.Sequential(*layers)#放在同一个元组
cfgs = {
'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}
def vgg(model_name="vgg16", **kwargs):
assert model_name in cfgs, "Warning: model number {} not in cfgs dict!".format(model_name)
cfg = cfgs[model_name]
model = VGG(make_features(cfg), **kwargs)
return model
net = vgg("vgg13")
print(net)3.1GoogleNet
网络中的新颖处
1、引入了Inception结构（融合同尺度的特征信息）
2、使用1×1卷积核进行降维
3、使用两个辅助分类器
4、使用平均池化而不是最大池化
Inception包含一系列并行结构，但是每个分支的特征矩阵需要长宽一样。
辅助分类器其结构都为一个平均下采样层->1×1卷积层->两个全连接层->softmax激活函数，在训练时使用，预测时不使用辅助分类器。
#3×3reduce对应着#3×3之前的1×1的卷积，用来降维，类似#5×5，其总体结构如下图所示：
3.2GoogleNet构建
import torch.nn as nn
import torch
import torch.nn.functional as F
class GoogLeNet(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
super(GoogLeNet, self).__init__()
self.aux_logits = aux_logits
self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.conv2 = BasicConv2d(64, 64, kernel_size=1)
self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
if self.aux_logits:
self.aux1 = InceptionAux(512, num_classes)
self.aux2 = InceptionAux(528, num_classes)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(0.4)
self.fc = nn.Linear(1024, num_classes)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N x 3 x 224 x 224
x = self.conv1(x)
# N x 64 x 112 x 112
x = self.maxpool1(x)
# N x 64 x 56 x 56
x = self.conv2(x)
# N x 64 x 56 x 56
x = self.conv3(x)
# N x 192 x 56 x 56
x = self.maxpool2(x)
# N x 192 x 28 x 28
x = self.inception3a(x)
# N x 256 x 28 x 28
x = self.inception3b(x)
# N x 480 x 28 x 28
x = self.maxpool3(x)
# N x 480 x 14 x 14
x = self.inception4a(x)
# N x 512 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux1 = self.aux1(x)
x = self.inception4b(x)
# N x 512 x 14 x 14
x = self.inception4c(x)
# N x 512 x 14 x 14
x = self.inception4d(x)
# N x 528 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux2 = self.aux2(x)
x = self.inception4e(x)
# N x 832 x 14 x 14
x = self.maxpool4(x)
# N x 832 x 7 x 7
x = self.inception5a(x)
# N x 832 x 7 x 7
x = self.inception5b(x)
# N x 1024 x 7 x 7
x = self.avgpool(x)
# N x 1024 x 1 x 1
x = torch.flatten(x, 1)
# N x 1024
x = self.dropout(x)
x = self.fc(x)
# N x 1000 (num_classes)
if self.training and self.aux_logits: # eval model lose this layer
return x, aux2, aux1
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
class Inception(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(Inception, self).__init__()
self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
self.branch2 = nn.Sequential(
BasicConv2d(in_channels, ch3x3red, kernel_size=1),
BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1) # 保证输出大小等于输入大小
)
self.branch3 = nn.Sequential(
BasicConv2d(in_channels, ch5x5red, kernel_size=1),
BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2) # 保证输出大小等于输入大小
)
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
BasicConv2d(in_channels, pool_proj, kernel_size=1)
)
def forward(self, x):
branch1 = self.branch1(x)
branch2 = self.branch2(x)
branch3 = self.branch3(x)
branch4 = self.branch4(x)
outputs = [branch1, branch2, branch3, branch4]
return torch.cat(outputs, 1)#channel维度进行合并
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, num_classes)
def forward(self, x):
# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
x = self.averagePool(x)
# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
x = self.conv(x)
# N x 128 x 4 x 4
x = torch.flatten(x, 1)
x = F.dropout(x, 0.5, training=self.training)
# N x 2048
x = F.relu(self.fc1(x), inplace=True)
x = F.dropout(x, 0.5, training=self.training)
# N x 1024
x = self.fc2(x)
# N x num_classes
return x
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.relu(x)
return x
4 、引用
霹雳吧啦Wz的个人空间_哔哩哔哩_Bilibili
ImageNet Classification with Deep Convolutional Neural Networks
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
Going Deeper with convolutions