[GoogLeNet]Inception-v4

参考：Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning，解析Inception-v4架构

总体架构

各个模块输出如下：

All the convolutions not marked with “V” in the figures are same-padded meaning that their output grid matches the size of their input. Convolutions marked with “V” are valid padded, meaning that input patch of each unit is fully contained in the previous layer and the grid size of the output activation map is reduced accordingly

在下面各个模块的结构图中，没有加符号的表示其输出数据体的空间尺寸和输入相同；加符号的表示输出数据体空间尺寸进行了衰减

Stem

Stem模块实现了网络早期运算，推导如下：

Inception-A

这是GoogLeNet_BN使用的Inception架构，推导如下：

Reduction-A

模块Reduction-A实现空间尺寸缩减功能，从。其超参数

Inception-B

模块Inception-B使用了Inception-3模型中的分解卷积模块，其参数如下表所示

type	patch size/stride	input size	output size	depth	#1x1	#1x7	#7x1	#1x7	#7x1
conv		17x17x1024	17x17x384	1	384
conv		17x17x1024	17x17x256	3	192	224	256
conv		17x17x1024	17x17x256	5	192	192	224	224	256
avg pooling	3x3/1	17x17x1024	17x17x128	2	128

Reduction-B

type	patch size/stride	input size	output size	depth	#1x1	#1x7	#7x1	#3x3
conv	stride=2	17x17x1024	8x8x192	2	192			192
conv	stride=2	17x17x1024	8x8x320	4	256	256	320	320
max pooling	3x3/2	17x17x1024	8x8x1024	1

Inception-C

实现

分别定义上述6个模块，然后定义Inception_v4模型，完整实现参考inception_v4.py