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连接池实现示例程序
Nov 26 Python
python使用itchat库实现微信机器人(好友聊天、群聊天)
Jan 04 Python
python模仿网页版微信发送消息功能
Feb 24 Python
Python基于更相减损术实现求解最大公约数的方法
Apr 04 Python
Python实现的基于优先等级分配糖果问题算法示例
Apr 25 Python
python pandas 对series和dataframe的重置索引reindex方法
Jun 07 Python
解决python Markdown模块乱码的问题
Feb 14 Python
Python 给屏幕打印信息加上颜色的实现方法
Apr 24 Python
关于Python作用域自学总结
Jun 10 Python
在python tkinter中Canvas实现进度条显示的方法
Jun 14 Python
使用python将mysql数据库的数据转换为json数据的方法
Jul 01 Python
PyTorch: Softmax多分类实战操作
Jul 07 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
使用php将某个目录下面的所有文件罗列出来的方法详解
2013/06/21 PHP
分享下PHP register_globals 值为on与off的理解
2013/09/26 PHP
php smarty模板引擎的6个小技巧
2014/04/24 PHP
yii2带搜索功能的下拉框实例详解
2016/05/12 PHP
thinkPHP5实现的查询数据库并返回json数据实例
2017/10/23 PHP
PHP实现双链表删除与插入节点的方法示例
2017/11/11 PHP
PHP操作Redis数据库常用方法示例
2018/08/25 PHP
一个简单的js动画效果代码
2010/07/20 Javascript
javascript中substr,substring,slice.splice的区别说明
2010/11/25 Javascript
jquery分页插件AmSetPager(自写)
2013/04/15 Javascript
jQuery ui插件的使用方法代码实例
2013/05/08 Javascript
使用js在页面中绘制表格核心代码
2013/09/16 Javascript
JavaScript Ajax Json实现上下级下拉框联动效果实例代码
2013/11/23 Javascript
jQuery 获取兄弟元素的几种不错方法
2014/05/23 Javascript
JavaScript中常见的字符串操作函数及用法汇总
2015/05/04 Javascript
基于jquery实现图片上传本地预览功能
2016/01/08 Javascript
基于jQuery实现动态搜索显示功能
2016/05/05 Javascript
jQuery中 bind的用法简单介绍
2017/02/13 Javascript
js中的DOM模拟购物车功能
2017/03/22 Javascript
vue内置组件transition简单原理图文详解(小结)
2018/07/12 Javascript
webpack@v4升级踩坑(小结)
2018/10/08 Javascript
Vue中的组件及路由使用实例代码详解
2019/05/22 Javascript
基于vue项目设置resolves.alias: '@'路径并适配webstorm
2020/12/02 Vue.js
TensorFlow实现简单卷积神经网络
2018/05/24 Python
对python GUI实现完美进度条的示例详解
2018/12/13 Python
Python3+Appium实现多台移动设备操作的方法
2019/07/05 Python
Python响应对象text属性乱码解决方案
2020/03/31 Python
python 数据库查询返回list或tuple实例
2020/05/15 Python
python3中calendar返回某一时间点实例讲解
2020/11/18 Python
Python基于template实现字符串替换
2020/11/27 Python
服务之星获奖感言
2014/01/21 职场文书
四查四看剖析材料
2014/02/14 职场文书
国家机关领导干部民主生活会对照检查材料思想汇报
2014/09/17 职场文书
财务统计员岗位职责
2015/04/14 职场文书
幼儿教师三分钟演讲稿
2019/06/21 职场文书
Python使用OpenCV实现虚拟缩放效果
2022/02/28 Python