InceptionV1 module
1 . 采用不同大小的卷积核意味着不同大小的感受野，最后拼接意味着不同尺度特征的融合；
2 . 卷积核大小采用1、3和5，主要是为了方便对齐。设定卷积步长stride=1之后，只要分别设定pad=0、1、2，那么卷积之后便可以得到相同维度的特征，然后这些特征就可以直接拼接在一起了；
3 . 文章说很多地方都表明pooling挺有效，所以Inception里面也嵌入了。
4 . 网络越到后面，特征越抽象，而且每个特征所涉及的感受野也更大了，因此随着层数的增加，3x3和5x5卷积的比例也要增加。
GoogLeNet网络结构图
（1）显然GoogLeNet采用了Inception模块化（9个）的结构，共22层，方便增添和修改；
（2）网络最后采用了average pooling来代替全连接层，想法来自NIN,参数量仅为AlexNet的1/12,性能优于AlexNet，事实证明可以将TOP1 accuracy提高0.6%。但是，实际在最后还是加了一个全连接层，主要是为了方便finetune；
（3）虽然移除了全连接，但是网络中依然使用了Dropout ;
（4）为了避免梯度消失，网络额外增加了2个辅助的softmax用于向前传导梯度。文章中说这两个辅助的分类器的loss应该加一个衰减系数，但看caffe中的model也没有加任何衰减。此外，实际测试的时候，这两个额外的softmax会被去掉。
PyTorch实现GoogLeNet
import torch
import torch.nn as nn
import torchvision
def ConvBNReLU(in_channels,out_channels,kernel_size):
return nn.Sequential(
nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=1,padding=kernel_size//2),
nn.BatchNorm2d(out_channels),
nn.ReLU6(inplace=True)
)
class InceptionV1Module(nn.Module):
def __init__(self, in_channels,out_channels1, out_channels2reduce,out_channels2, out_channels3reduce, out_channels3, out_channels4):
super(InceptionV1Module, self).__init__()
self.branch1_conv = ConvBNReLU(in_channels=in_channels,out_channels=out_channels1,kernel_size=1)
self.branch2_conv1 = ConvBNReLU(in_channels=in_channels,out_channels=out_channels2reduce,kernel_size=1)
self.branch2_conv2 = ConvBNReLU(in_channels=out_channels2reduce,out_channels=out_channels2,kernel_size=3)
self.branch3_conv1 = ConvBNReLU(in_channels=in_channels, out_channels=out_channels3reduce, kernel_size=1)
self.branch3_conv2 = ConvBNReLU(in_channels=out_channels3reduce, out_channels=out_channels3, kernel_size=5)
self.branch4_pool = nn.MaxPool2d(kernel_size=3,stride=1,padding=1)
self.branch4_conv1 = ConvBNReLU(in_channels=in_channels, out_channels=out_channels4, kernel_size=1)
def forward(self,x):
out1 = self.branch1_conv(x)
out2 = self.branch2_conv2(self.branch2_conv1(x))
out3 = self.branch3_conv2(self.branch3_conv1(x))
out4 = self.branch4_conv1(self.branch4_pool(x))
out = torch.cat([out1, out2, out3, out4], dim=1)
return out
class InceptionAux(nn.Module):
def __init__(self, in_channels,out_channels):
super(InceptionAux, self).__init__()
self.auxiliary_avgpool = nn.AvgPool2d(kernel_size=5, stride=3)
self.auxiliary_conv1 = ConvBNReLU(in_channels=in_channels, out_channels=128, kernel_size=1)
self.auxiliary_linear1 = nn.Linear(in_features=128 * 4 * 4, out_features=1024)
self.auxiliary_relu = nn.ReLU6(inplace=True)
self.auxiliary_dropout = nn.Dropout(p=0.7)
self.auxiliary_linear2 = nn.Linear(in_features=1024, out_features=out_channels)
def forward(self, x):
x = self.auxiliary_conv1(self.auxiliary_avgpool(x))
x = x.view(x.size(0), -1)
x= self.auxiliary_relu(self.auxiliary_linear1(x))
out = self.auxiliary_linear2(self.auxiliary_dropout(x))
return out
class InceptionV1(nn.Module):
def __init__(self, num_classes=1000, stage='train'):
super(InceptionV1, self).__init__()
self.stage = stage
self.block1 = nn.Sequential(
nn.Conv2d(in_channels=3,out_channels=64,kernel_size=7,stride=2,padding=3),
nn.BatchNorm2d(64),
nn.MaxPool2d(kernel_size=3,stride=2, padding=1),
nn.Conv2d(in_channels=64, out_channels=64, kernel_size=1, stride=1),
nn.BatchNorm2d(64),
)
self.block2 = nn.Sequential(
nn.Conv2d(in_channels=64, out_channels=192, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(192),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
)
self.block3 = nn.Sequential(
InceptionV1Module(in_channels=192,out_channels1=64, out_channels2reduce=96, out_channels2=128, out_channels3reduce = 16, out_channels3=32, out_channels4=32),
InceptionV1Module(in_channels=256, out_channels1=128, out_channels2reduce=128, out_channels2=192,out_channels3reduce=32, out_channels3=96, out_channels4=64),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
)
self.block4_1 = InceptionV1Module(in_channels=480, out_channels1=192, out_channels2reduce=96, out_channels2=208,out_channels3reduce=16, out_channels3=48, out_channels4=64)
if self.stage == 'train':
self.aux_logits1 = InceptionAux(in_channels=512,out_channels=num_classes)
self.block4_2 = nn.Sequential(
InceptionV1Module(in_channels=512, out_channels1=160, out_channels2reduce=112, out_channels2=224,
out_channels3reduce=24, out_channels3=64, out_channels4=64),
InceptionV1Module(in_channels=512, out_channels1=128, out_channels2reduce=128, out_channels2=256,
out_channels3reduce=24, out_channels3=64, out_channels4=64),
InceptionV1Module(in_channels=512, out_channels1=112, out_channels2reduce=144, out_channels2=288,
out_channels3reduce=32, out_channels3=64, out_channels4=64),
)
if self.stage == 'train':
self.aux_logits2 = InceptionAux(in_channels=528,out_channels=num_classes)
self.block4_3 = nn.Sequential(
InceptionV1Module(in_channels=528, out_channels1=256, out_channels2reduce=160, out_channels2=320,
out_channels3reduce=32, out_channels3=128, out_channels4=128),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
)
self.block5 = nn.Sequential(
InceptionV1Module(in_channels=832, out_channels1=256, out_channels2reduce=160, out_channels2=320,out_channels3reduce=32, out_channels3=128, out_channels4=128),
InceptionV1Module(in_channels=832, out_channels1=384, out_channels2reduce=192, out_channels2=384,out_channels3reduce=48, out_channels3=128, out_channels4=128),
)
self.avgpool = nn.AvgPool2d(kernel_size=7,stride=1)
self.dropout = nn.Dropout(p=0.4)
self.linear = nn.Linear(in_features=1024,out_features=num_classes)
def forward(self, x):
x = self.block1(x)
x = self.block2(x)
x = self.block3(x)
aux1 = x = self.block4_1(x)
aux2 = x = self.block4_2(x)
x = self.block4_3(x)
out = self.block5(x)
out = self.avgpool(out)
out = self.dropout(out)
out = out.view(out.size(0), -1)
out = self.linear(out)
if self.stage == 'train':
aux1 = self.aux_logits1(aux1)
aux2 = self.aux_logits2(aux2)
return aux1, aux2, out
else:
return out
if __name__=='__main__':
model = InceptionV1()
print(model)
input = torch.randn(1, 3, 224, 224)
aux1, aux2, out = model(input)
print(aux1.shape)
print(aux2.shape)
print(out.shape)
