GoogLeNet之InceptionV3神经网络简介与代码实战

AI洲抿嘴的薯片

已于 2024-10-17 21:58:03 修改

阅读量391

点赞数

分类专栏：深度学习CNN模型实战文章标签：神经网络深度学习人工智能

于 2023-05-22 17:12:42 首次发布

本文链接：https://blog.csdn.net/m0_59023219/article/details/130811204

版权

深度学习CNN模型实战专栏收录该内容

18 篇文章 1 订阅

订阅专栏

InceptionV3在InceptionV2基础上优化了模型结构，如使用1xN和Nx1卷积减少参数量，适用于中等大小的特征图。文章介绍了InceptionV3的两个子结构InceptionV3a和InceptionV3b，并提供了Keras代码实现这两个子结构的详细过程。

摘要由CSDN通过智能技术生成

1.介绍

Inception V3与Inception V2是来自于同一篇论文，具体可以参见论文Rethinking the Inception Architecture for Computer Vision中。

2.模型结构

InceptionV3 a子结构

InceptionV3 b子结构

3.模型特点
Inception V3相比Inception V2进行了如下改进: 任意nxn的卷积都可以通过1xn卷积后接nx1卷积来替代，进一步减少参数量，但在实际上，作者发现在网络的前期使用这种分解效果并不好，只有在中度大小的feature map上使用效果才会更好，对于mxm大小的feature map,建议m在12到20之间。

4.代码实现 keras

def Conv2d(x, nb_filter, kernel_size, padding='same', strides=(1, 1)):
    x = Conv2D(nb_filter, kernel_size, padding=padding, strides=strides)(x)
    x = BatchNormalization(axis=3)(x)
    x = Activation('relu')(x)
    return x
 
 
def Inception_a(x, nb_filter=[128, 192]):
    branch0 = Conv2d(x, nb_filter[0], (1, 1), padding='same', strides=(1, 1))
    branch0 = Conv2d(branch0, nb_filter[0], (7, 1), padding='same', strides=(1, 1))
    branch0 = Conv2d(branch0, nb_filter[0], (1, 7), padding='same', strides=(1, 1))
    branch0 = Conv2d(branch0, nb_filter[0], (7, 1), padding='same', strides=(1, 1))
    branch0 = Conv2d(branch0, nb_filter[1], (1, 7), padding='same', strides=(1, 1))
 
    branch1 = Conv2d(x, nb_filter[0], (1, 1), padding='same', strides=(1, 1))
    branch1 = Conv2d(branch1, nb_filter[0], (7, 1), padding='same', strides=(1, 1))
    branch1 = Conv2d(branch1, nb_filter[1], (1, 7), padding='same', strides=(1, 1))
    
    branch2 = MaxPooling2D(pool_size=(3, 3), strides=(1, 1), padding='same')(x)
    branch2 = Conv2d(branch2, nb_filter[1], (1, 1), padding='same', strides=(1, 1))
    
    branch3 = Conv2d(x, nb_filter[1], (1, 1), padding='same', strides=(1, 1))
    
    x = concatenate([branch0, branch1, branch2, branch3], axis=3)
 
    return x
 
 
def Inception_b(x, nb_filter=[448, 384, 192, 320]):
    branch0 = Conv2d(x, nb_filter[0], (1, 1), padding='same', strides=(1, 1))
    branch0 = Conv2d(branch0, nb_filter[1], (3, 3), padding='same', strides=(1, 1))
    branch0_1 = Conv2d(branch0, nb_filter[1], (3, 1), padding='same', strides=(1, 1))
    branch0_2 = Conv2d(branch0, nb_filter[1], (1, 3), padding='same', strides=(1, 1))
 
    branch1 = Conv2d(x, nb_filter[1], (1, 1), padding='same', strides=(1, 1))
    branch1_1 = Conv2d(branch1, nb_filter[1], (3, 1), padding='same', strides=(1, 1))
    branch1_2 = Conv2d(branch1, nb_filter[1], (1, 3), padding='same', strides=(1, 1))
    
    branch2 = MaxPooling2D(pool_size=(3, 3), strides=(1, 1), padding='same')(x)
    branch2 = Conv2d(branch2, nb_filter[2], (1, 1), padding='same', strides=(1, 1))
    
    branch3 = Conv2d(x, nb_filter[3], (1, 1), padding='same', strides=(1, 1))
    
    x = concatenate([branch0_1, branch0_2, branch1_1, branch1_2, branch2, branch3], axis=3)
    
    return x