PYTHON InceptionV3模型的复现详解


Posted in Python onMay 06, 2022

学习前言

Inception系列的结构和其它的前向神经网络的结构不太一样,每一层的内容不是直直向下的,而是分了很多的块。

什么是InceptionV3模型

InceptionV3模型是谷歌Inception系列里面的第三代模型,其模型结构与InceptionV2模型放在了同一篇论文里,其实二者模型结构差距不大,相比于其它神经网络模型,Inception网络最大的特点在于将神经网络层与层之间的卷积运算进行了拓展。
如VGG,AlexNet网络,它就是一直卷积下来的,一层接着一层;
ResNet则是创新性的引入了残差网络的概念,使得靠前若干层的某一层数据输出直接跳过多层引入到后面数据层的输入部分,后面的特征层的内容会有一部分由其前面的某一层线性贡献。
而Inception网络则是采用不同大小的卷积核,使得存在不同大小的感受野,最后实现拼接达到不同尺度特征的融合。
对于InceptionV3而言,其网络中存在着如下的结构。
这个结构使用不同大小的卷积核对输入进行卷积(这个结构主要在代码中的block1使用)。
PYTHON InceptionV3模型的复现详解
还存在着这样的结构,利用1x7的卷积和7x1的卷积代替7x7的卷积,这样可以只使用约(1x7 + 7x1) / (7x7) = 28.6%的计算开销;利用1x3的卷积和3x1的卷积代替3x3的卷积,这样可以只使用约(1x3 + 3x1) / (3x3) = 67%的计算开销。
下图利用1x7的卷积和7x1的卷积代替7x7的卷积(这个结构主要在代码中的block2使用)。
PYTHON InceptionV3模型的复现详解
下图利用1x3的卷积和3x1的卷积代替3x3的卷积(这个结构主要在代码中的block3使用)。
PYTHON InceptionV3模型的复现详解

InceptionV3网络部分实现代码

我一共将InceptionV3划分为3个block,对应着35x35、17x17,8x8维度大小的图像。每个block中间有许多的part,对应着不同的特征层深度,用于特征提取。

#-------------------------------------------------------------#
#   InceptionV3的网络部分
#-------------------------------------------------------------#
from __future__ import print_function
from __future__ import absolute_import

import warnings
import numpy as np

from keras.models import Model
from keras import layers
from keras.layers import Activation,Dense,Input,BatchNormalization,Conv2D,MaxPooling2D,AveragePooling2D
from keras.layers import GlobalAveragePooling2D,GlobalMaxPooling2D
from keras.engine.topology import get_source_inputs
from keras.utils.layer_utils import convert_all_kernels_in_model
from keras.utils.data_utils import get_file
from keras import backend as K
from keras.applications.imagenet_utils import decode_predictions
from keras.preprocessing import image


def conv2d_bn(x,
              filters,
              num_row,
              num_col,
              padding='same',
              strides=(1, 1),
              name=None):
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    x = Conv2D(
        filters, (num_row, num_col),
        strides=strides,
        padding=padding,
        use_bias=False,
        name=conv_name)(x)
    x = BatchNormalization(scale=False, name=bn_name)(x)
    x = Activation('relu', name=name)(x)
    return x


def InceptionV3(input_shape=[299,299,3],
                classes=1000):


    img_input = Input(shape=input_shape)

    x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
    x = conv2d_bn(x, 32, 3, 3, padding='valid')
    x = conv2d_bn(x, 64, 3, 3)
    x = MaxPooling2D((3, 3), strides=(2, 2))(x)

    x = conv2d_bn(x, 80, 1, 1, padding='valid')
    x = conv2d_bn(x, 192, 3, 3, padding='valid')
    x = MaxPooling2D((3, 3), strides=(2, 2))(x)

    #--------------------------------#
    #   Block1 35x35
    #--------------------------------#
    # Block1 part1
    # 35 x 35 x 192 -> 35 x 35 x 256
    branch1x1 = conv2d_bn(x, 64, 1, 1)

    branch5x5 = conv2d_bn(x, 48, 1, 1)
    branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)

    branch3x3dbl = conv2d_bn(x, 64, 1, 1)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)

    branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
    branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
    x = layers.concatenate(
        [branch1x1, branch5x5, branch3x3dbl, branch_pool],
        axis=3,
        name='mixed0')

    # Block1 part2
    # 35 x 35 x 256 -> 35 x 35 x 288
    branch1x1 = conv2d_bn(x, 64, 1, 1)

    branch5x5 = conv2d_bn(x, 48, 1, 1)
    branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)

    branch3x3dbl = conv2d_bn(x, 64, 1, 1)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)

    branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
    branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
    x = layers.concatenate(
        [branch1x1, branch5x5, branch3x3dbl, branch_pool],
        axis=3,
        name='mixed1')

    # Block1 part3
    # 35 x 35 x 288 -> 35 x 35 x 288
    branch1x1 = conv2d_bn(x, 64, 1, 1)

    branch5x5 = conv2d_bn(x, 48, 1, 1)
    branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)

    branch3x3dbl = conv2d_bn(x, 64, 1, 1)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)

    branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
    branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
    x = layers.concatenate(
        [branch1x1, branch5x5, branch3x3dbl, branch_pool],
        axis=3,
        name='mixed2')

    #--------------------------------#
    #   Block2 17x17
    #--------------------------------#
    # Block2 part1
    # 35 x 35 x 288 -> 17 x 17 x 768
    branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')

    branch3x3dbl = conv2d_bn(x, 64, 1, 1)
    branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
    branch3x3dbl = conv2d_bn(
        branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')

    branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
    x = layers.concatenate(
        [branch3x3, branch3x3dbl, branch_pool], axis=3, name='mixed3')

    # Block2 part2
    # 17 x 17 x 768 -> 17 x 17 x 768
    branch1x1 = conv2d_bn(x, 192, 1, 1)

    branch7x7 = conv2d_bn(x, 128, 1, 1)
    branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
    branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)

    branch7x7dbl = conv2d_bn(x, 128, 1, 1)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)

    branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
    branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
    x = layers.concatenate(
        [branch1x1, branch7x7, branch7x7dbl, branch_pool],
        axis=3,
        name='mixed4')

    # Block2 part3 and part4
    # 17 x 17 x 768 -> 17 x 17 x 768 -> 17 x 17 x 768
    for i in range(2):
        branch1x1 = conv2d_bn(x, 192, 1, 1)

        branch7x7 = conv2d_bn(x, 160, 1, 1)
        branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
        branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)

        branch7x7dbl = conv2d_bn(x, 160, 1, 1)
        branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
        branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
        branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
        branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)

        branch_pool = AveragePooling2D(
            (3, 3), strides=(1, 1), padding='same')(x)
        branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
        x = layers.concatenate(
            [branch1x1, branch7x7, branch7x7dbl, branch_pool],
            axis=3,
            name='mixed' + str(5 + i))

    # Block2 part5
    # 17 x 17 x 768 -> 17 x 17 x 768
    branch1x1 = conv2d_bn(x, 192, 1, 1)

    branch7x7 = conv2d_bn(x, 192, 1, 1)
    branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
    branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)

    branch7x7dbl = conv2d_bn(x, 192, 1, 1)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
    branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)

    branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
    branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
    x = layers.concatenate(
        [branch1x1, branch7x7, branch7x7dbl, branch_pool],
        axis=3,
        name='mixed7')

    #--------------------------------#
    #   Block3 8x8
    #--------------------------------#
    # Block3 part1
    # 17 x 17 x 768 -> 8 x 8 x 1280
    branch3x3 = conv2d_bn(x, 192, 1, 1)
    branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
                          strides=(2, 2), padding='valid')

    branch7x7x3 = conv2d_bn(x, 192, 1, 1)
    branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
    branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
    branch7x7x3 = conv2d_bn(
        branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')

    branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
    x = layers.concatenate(
        [branch3x3, branch7x7x3, branch_pool], axis=3, name='mixed8')

    # Block3 part2 part3
    # 8 x 8 x 1280 -> 8 x 8 x 2048 -> 8 x 8 x 2048
    for i in range(2):
        branch1x1 = conv2d_bn(x, 320, 1, 1)

        branch3x3 = conv2d_bn(x, 384, 1, 1)
        branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
        branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
        branch3x3 = layers.concatenate(
            [branch3x3_1, branch3x3_2], axis=3, name='mixed9_' + str(i))

        branch3x3dbl = conv2d_bn(x, 448, 1, 1)
        branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
        branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
        branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
        branch3x3dbl = layers.concatenate(
            [branch3x3dbl_1, branch3x3dbl_2], axis=3)

        branch_pool = AveragePooling2D(
            (3, 3), strides=(1, 1), padding='same')(x)
        branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
        x = layers.concatenate(
            [branch1x1, branch3x3, branch3x3dbl, branch_pool],
            axis=3,
            name='mixed' + str(9 + i))
    # 平均池化后全连接。
    x = GlobalAveragePooling2D(name='avg_pool')(x)
    x = Dense(classes, activation='softmax', name='predictions')(x)


    inputs = img_input

    model = Model(inputs, x, name='inception_v3')

    return model

图片预测

建立网络后,可以用以下的代码进行预测。

def preprocess_input(x):
    x /= 255.
    x -= 0.5
    x *= 2.
    return x


if __name__ == '__main__':
    model = InceptionV3()

    model.load_weights("inception_v3_weights_tf_dim_ordering_tf_kernels.h5")
    
    img_path = 'elephant.jpg'
    img = image.load_img(img_path, target_size=(299, 299))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)

    x = preprocess_input(x)

    preds = model.predict(x)
    print('Predicted:', decode_predictions(preds))

预测所需的已经训练好的InceptionV3模型可以在https://github.com/fchollet/deep-learning-models/releases下载。非常方便。
预测结果为:

Predicted: [[('n02504458', 'African_elephant', 0.50874853), ('n01871265', 'tusker', 0.19524273), ('n02504013', 'Indian_elephant', 0.1566972), ('n01917289', 'brain_coral', 0.0008956835), ('n01695060', 'Komodo_dragon', 0.0008260256)]]

这里我推荐一个很不错的blog讲InceptionV3的结构的深度神经网络Google Inception Net-V3结构图里面有每一层的结构图,非常清晰。


Tags in this post...

Python 相关文章推荐
python定时采集摄像头图像上传ftp服务器功能实现
Dec 23 Python
更改Python命令行交互提示符的方法
Jan 14 Python
Python实现自动登录百度空间的方法
Jun 10 Python
Python模拟脉冲星伪信号频率实例代码
Jan 03 Python
详解Tensorflow数据读取有三种方式(next_batch)
Feb 01 Python
使用Python计算玩彩票赢钱概率
Jun 26 Python
基于Django框架的权限组件rbac实例讲解
Aug 31 Python
PyTorch学习:动态图和静态图的例子
Jan 06 Python
django和flask哪个值得研究学习
Jul 31 Python
Python读取Excel一列并计算所有对象出现次数的方法
Sep 04 Python
python使用pywinauto驱动微信客户端实现公众号爬虫
May 19 Python
python获取带有返回值的多线程
May 02 Python
代码复现python目标检测yolo3详解预测
讲解Python实例练习逆序输出字符串
May 06 #Python
python turtle绘图
May 04 #Python
python blinker 信号库
May 04 #Python
python三子棋游戏
May 04 #Python
python神经网络 使用Keras构建RNN训练
May 04 #Python
python神经网络学习 使用Keras进行回归运算
May 04 #Python
You might like
缅甸的咖啡简史
2021/03/04 咖啡文化
php 动态多文件上传
2009/01/18 PHP
解析PHP多种序列化与反序列化的方法
2013/06/06 PHP
php使用explode()函数将字符串拆分成数组的方法
2015/02/17 PHP
两种php给图片加水印的实现代码
2020/04/18 PHP
详解EventDispatcher事件分发组件
2016/12/25 PHP
jquery each()源代码
2011/02/14 Javascript
Jquery中Ajax 缓存带来的影响的解决方法
2011/05/19 Javascript
基于jquery的无刷新分页技术
2011/06/11 Javascript
原生JS实现表单checkbook获取已选择的值
2013/07/21 Javascript
checkbox全选所涉及到的知识点介绍
2013/12/31 Javascript
JavaScript基本类型值-Undefined、Null、Boolean
2017/02/23 Javascript
微信小程序遇到修改数据后页面不渲染的问题解决
2017/03/09 Javascript
vue中锚点的三种方法
2018/07/06 Javascript
Vue编程式跳转的实例代码详解
2019/07/10 Javascript
Node.js fs模块(文件模块)创建、删除目录(文件)读取写入文件流的方法
2019/09/03 Javascript
Python 中迭代器与生成器实例详解
2017/03/29 Python
Python常用时间操作总结【取得当前时间、时间函数、应用等】
2017/05/11 Python
Pycharm 设置自定义背景颜色的图文教程
2018/05/23 Python
numpy数组广播的机制
2019/07/12 Python
利用python制作拼图小游戏的全过程
2020/12/04 Python
css 省略号 css3让多余的字符串消失并附加省略号的实现代码
2013/02/07 HTML / CSS
解锁canvas导出图片跨域的N种姿势小结
2019/01/24 HTML / CSS
整个世界的设计师家具在哈恩:Designathome
2019/03/25 全球购物
大学生毕业自我鉴定范文
2013/11/03 职场文书
高中毕业的自我鉴定
2013/12/09 职场文书
乡镇庆八一活动方案
2014/02/02 职场文书
一体化教学实施方案
2014/05/10 职场文书
公司授权委托书范本
2014/09/18 职场文书
学生检讨书怎么写
2014/10/09 职场文书
2016公司年会通知范文
2015/04/25 职场文书
Navicat for MySQL的使用教程详解
2021/05/27 MySQL
Spring boot应用启动后首次访问很慢的解决方案
2021/06/23 Java/Android
JS创建或填充任意长度数组的小技巧汇总
2021/10/24 Javascript
java项目构建Gradle的使用教程
2022/03/24 Java/Android
Windows 64位 安装 mysql 8.0.28 图文教程
2022/04/19 MySQL