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魔法方法-自定义序列详解
Jul 21 Python
详解如何用OpenCV + Python 实现人脸识别
Oct 20 Python
利用python编写一个图片主色转换的脚本
Dec 07 Python
Python 文本文件内容批量抽取实例
Dec 10 Python
Python实现的爬取百度文库功能示例
Feb 16 Python
Python代码实现删除一个list里面重复元素的方法
Apr 02 Python
python 整数越界问题详解
Jun 27 Python
Python 类方法和实例方法(@classmethod),静态方法(@staticmethod)原理与用法分析
Sep 20 Python
python GUI库图形界面开发之PyQt5信号与槽的高级使用技巧装饰器信号与槽详细使用方法与实例
Mar 06 Python
pip/anaconda修改镜像源,加快python模块安装速度的操作
Mar 04 Python
python 实现定时任务的四种方式
Apr 01 Python
python not运算符的实例用法
Jun 30 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
关于拼配咖啡,你要知道
2021/03/03 咖啡文化
yii2中使用Active Record模式的方法
2016/01/09 PHP
Laravel框架实现即点即改功能的方法分析
2019/10/31 PHP
nicejforms——美化表单不用愁
2007/02/20 Javascript
javascript AutoScroller 函数类
2009/05/29 Javascript
用Javascript 获取页面元素的位置的代码
2009/09/25 Javascript
jquery实现带单选按钮的表格行选中时高亮显示
2013/08/01 Javascript
原生js和jQuery实现淡入淡出轮播效果
2015/12/25 Javascript
微信小程序 Audio API详解及实例代码
2016/09/30 Javascript
jQuery.Validate表单验证插件的使用示例详解
2017/01/04 Javascript
Vue + Webpack + Vue-loader学习教程之相关配置篇
2017/03/14 Javascript
HTML的select控件美化
2017/03/27 Javascript
webpack构建的详细流程探底
2018/01/08 Javascript
JS原生带缩略图的图片切换效果
2018/10/10 Javascript
使用vue完成微信公众号网页小记(推荐)
2019/04/28 Javascript
nodejs如何在package.json中设置多条启动命令
2020/03/16 NodeJs
vantUI 获得piker选中值的自定义ID操作
2020/11/04 Javascript
python数组复制拷贝的实现方法
2015/06/09 Python
python列出目录下指定文件与子目录的方法
2015/07/03 Python
Python的for和break循环结构中使用else语句的技巧
2016/05/24 Python
Python简单遍历字典及删除元素的方法
2016/09/18 Python
Python编程django实现同一个ip十分钟内只能注册一次
2017/11/03 Python
Python实现的归并排序算法示例
2017/11/21 Python
基于Python列表解析(列表推导式)
2018/06/23 Python
简单了解Python生成器是什么
2019/07/02 Python
ML神器:sklearn的快速使用及入门
2019/07/11 Python
Python实现多线程/多进程的TCP服务器
2019/09/03 Python
css3 iphone玻璃透明气泡完美实现
2013/03/20 HTML / CSS
新奥尔良珠宝:Mignon Faget
2020/11/23 全球购物
行政专员工作职责
2013/12/22 职场文书
化工专业自荐书
2014/06/16 职场文书
2014大四本科生自我鉴定总结
2014/10/04 职场文书
2014年教师业务工作总结
2014/12/19 职场文书
一般纳税人申请报告
2015/05/18 职场文书
平凡的世界读书笔记
2015/06/25 职场文书
Python 用户输入和while循环的操作
2021/05/23 Python