1、 the YOLO model （YOLO ，you only look once）

（1）We will use 5 anchor boxes. So you can think of the YOLO architecture as the following: IMAGE (m, 608, 608, 3) -> DEEP CNN -> ENCODING (m, 19, 19, 5, 85).

（2）Training a YOLO model takes a very long time and requires a fairly large dataset of labelled bounding boxes for a large range of target classes. We are going to load an existing pretrained Keras YOLO model stored in "yolo.h5". (These weights come from the official YOLO website, and were converted using a function written by Allan Zelener.)

（3）model summry (模型信息)

Layer (type)                     Output Shape          Param #     Connected to

====================================================================================================

input_1 (InputLayer)             (None, 608, 608, 3)   0

____________________________________________________________________________________________________

conv2d_1 (Conv2D)                (None, 608, 608, 32)  864         input_1[0][0]

____________________________________________________________________________________________________

batch_normalization_1 (BatchNorm (None, 608, 608, 32)  128         conv2d_1[0][0]

____________________________________________________________________________________________________

leaky_re_lu_1 (LeakyReLU)        (None, 608, 608, 32)  0           batch_normalization_1[0][0]

____________________________________________________________________________________________________

max_pooling2d_1 (MaxPooling2D)   (None, 304, 304, 32)  0           leaky_re_lu_1[0][0]

____________________________________________________________________________________________________

conv2d_2 (Conv2D)                (None, 304, 304, 64)  18432       max_pooling2d_1[0][0]

____________________________________________________________________________________________________

batch_normalization_2 (BatchNorm (None, 304, 304, 64)  256         conv2d_2[0][0]

____________________________________________________________________________________________________

leaky_re_lu_2 (LeakyReLU)        (None, 304, 304, 64)  0           batch_normalization_2[0][0]

____________________________________________________________________________________________________

max_pooling2d_2 (MaxPooling2D)   (None, 152, 152, 64)  0           leaky_re_lu_2[0][0]

____________________________________________________________________________________________________

conv2d_3 (Conv2D)                (None, 152, 152, 128) 73728       max_pooling2d_2[0][0]

____________________________________________________________________________________________________

batch_normalization_3 (BatchNorm (None, 152, 152, 128) 512         conv2d_3[0][0]

____________________________________________________________________________________________________

leaky_re_lu_3 (LeakyReLU)        (None, 152, 152, 128) 0           batch_normalization_3[0][0]

____________________________________________________________________________________________________

conv2d_4 (Conv2D)                (None, 152, 152, 64)  8192        leaky_re_lu_3[0][0]

____________________________________________________________________________________________________

batch_normalization_4 (BatchNorm (None, 152, 152, 64)  256         conv2d_4[0][0]

____________________________________________________________________________________________________

leaky_re_lu_4 (LeakyReLU)        (None, 152, 152, 64)  0           batch_normalization_4[0][0]

____________________________________________________________________________________________________

conv2d_5 (Conv2D)                (None, 152, 152, 128) 73728       leaky_re_lu_4[0][0]

____________________________________________________________________________________________________

batch_normalization_5 (BatchNorm (None, 152, 152, 128) 512         conv2d_5[0][0]

____________________________________________________________________________________________________

leaky_re_lu_5 (LeakyReLU)        (None, 152, 152, 128) 0           batch_normalization_5[0][0]

____________________________________________________________________________________________________

max_pooling2d_3 (MaxPooling2D)   (None, 76, 76, 128)   0           leaky_re_lu_5[0][0]

____________________________________________________________________________________________________

conv2d_6 (Conv2D)                (None, 76, 76, 256)   294912      max_pooling2d_3[0][0]

____________________________________________________________________________________________________

batch_normalization_6 (BatchNorm (None, 76, 76, 256)   1024        conv2d_6[0][0]

____________________________________________________________________________________________________

leaky_re_lu_6 (LeakyReLU)        (None, 76, 76, 256)   0           batch_normalization_6[0][0]

____________________________________________________________________________________________________

conv2d_7 (Conv2D)                (None, 76, 76, 128)   32768       leaky_re_lu_6[0][0]

____________________________________________________________________________________________________

batch_normalization_7 (BatchNorm (None, 76, 76, 128)   512         conv2d_7[0][0]

____________________________________________________________________________________________________

leaky_re_lu_7 (LeakyReLU)        (None, 76, 76, 128)   0           batch_normalization_7[0][0]

____________________________________________________________________________________________________

conv2d_8 (Conv2D)                (None, 76, 76, 256)   294912      leaky_re_lu_7[0][0]

____________________________________________________________________________________________________

batch_normalization_8 (BatchNorm (None, 76, 76, 256)   1024        conv2d_8[0][0]

____________________________________________________________________________________________________

leaky_re_lu_8 (LeakyReLU)        (None, 76, 76, 256)   0           batch_normalization_8[0][0]

____________________________________________________________________________________________________

max_pooling2d_4 (MaxPooling2D)   (None, 38, 38, 256)   0           leaky_re_lu_8[0][0]

____________________________________________________________________________________________________

conv2d_9 (Conv2D)                (None, 38, 38, 512)   1179648     max_pooling2d_4[0][0]

____________________________________________________________________________________________________

batch_normalization_9 (BatchNorm (None, 38, 38, 512)   2048        conv2d_9[0][0]

____________________________________________________________________________________________________

leaky_re_lu_9 (LeakyReLU)        (None, 38, 38, 512)   0           batch_normalization_9[0][0]

____________________________________________________________________________________________________

conv2d_10 (Conv2D)               (None, 38, 38, 256)   131072      leaky_re_lu_9[0][0]

____________________________________________________________________________________________________

batch_normalization_10 (BatchNor (None, 38, 38, 256)   1024        conv2d_10[0][0]

____________________________________________________________________________________________________

leaky_re_lu_10 (LeakyReLU)       (None, 38, 38, 256)   0           batch_normalization_10[0][0]

____________________________________________________________________________________________________

conv2d_11 (Conv2D)               (None, 38, 38, 512)   1179648     leaky_re_lu_10[0][0]

____________________________________________________________________________________________________

batch_normalization_11 (BatchNor (None, 38, 38, 512)   2048        conv2d_11[0][0]

____________________________________________________________________________________________________

leaky_re_lu_11 (LeakyReLU)       (None, 38, 38, 512)   0           batch_normalization_11[0][0]

____________________________________________________________________________________________________

conv2d_12 (Conv2D)               (None, 38, 38, 256)   131072      leaky_re_lu_11[0][0]

____________________________________________________________________________________________________

batch_normalization_12 (BatchNor (None, 38, 38, 256)   1024        conv2d_12[0][0]

____________________________________________________________________________________________________

leaky_re_lu_12 (LeakyReLU)       (None, 38, 38, 256)   0           batch_normalization_12[0][0]

____________________________________________________________________________________________________

conv2d_13 (Conv2D)               (None, 38, 38, 512)   1179648     leaky_re_lu_12[0][0]

____________________________________________________________________________________________________

batch_normalization_13 (BatchNor (None, 38, 38, 512)   2048        conv2d_13[0][0]

____________________________________________________________________________________________________

leaky_re_lu_13 (LeakyReLU)       (None, 38, 38, 512)   0           batch_normalization_13[0][0]

____________________________________________________________________________________________________

max_pooling2d_5 (MaxPooling2D)   (None, 19, 19, 512)   0           leaky_re_lu_13[0][0]

____________________________________________________________________________________________________

conv2d_14 (Conv2D)               (None, 19, 19, 1024)  4718592     max_pooling2d_5[0][0]

____________________________________________________________________________________________________

batch_normalization_14 (BatchNor (None, 19, 19, 1024)  4096        conv2d_14[0][0]

____________________________________________________________________________________________________

leaky_re_lu_14 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_14[0][0]

____________________________________________________________________________________________________

conv2d_15 (Conv2D)               (None, 19, 19, 512)   524288      leaky_re_lu_14[0][0]

____________________________________________________________________________________________________

batch_normalization_15 (BatchNor (None, 19, 19, 512)   2048        conv2d_15[0][0]

____________________________________________________________________________________________________

leaky_re_lu_15 (LeakyReLU)       (None, 19, 19, 512)   0           batch_normalization_15[0][0]

____________________________________________________________________________________________________

conv2d_16 (Conv2D)               (None, 19, 19, 1024)  4718592     leaky_re_lu_15[0][0]

____________________________________________________________________________________________________

batch_normalization_16 (BatchNor (None, 19, 19, 1024)  4096        conv2d_16[0][0]

____________________________________________________________________________________________________

leaky_re_lu_16 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_16[0][0]

____________________________________________________________________________________________________

conv2d_17 (Conv2D)               (None, 19, 19, 512)   524288      leaky_re_lu_16[0][0]

____________________________________________________________________________________________________

batch_normalization_17 (BatchNor (None, 19, 19, 512)   2048        conv2d_17[0][0]

____________________________________________________________________________________________________

leaky_re_lu_17 (LeakyReLU)       (None, 19, 19, 512)   0           batch_normalization_17[0][0]

____________________________________________________________________________________________________

conv2d_18 (Conv2D)               (None, 19, 19, 1024)  4718592     leaky_re_lu_17[0][0]

____________________________________________________________________________________________________

batch_normalization_18 (BatchNor (None, 19, 19, 1024)  4096        conv2d_18[0][0]

____________________________________________________________________________________________________

leaky_re_lu_18 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_18[0][0]

____________________________________________________________________________________________________

conv2d_19 (Conv2D)               (None, 19, 19, 1024)  9437184     leaky_re_lu_18[0][0]

____________________________________________________________________________________________________

batch_normalization_19 (BatchNor (None, 19, 19, 1024)  4096        conv2d_19[0][0]

____________________________________________________________________________________________________

conv2d_21 (Conv2D)               (None, 38, 38, 64)    32768       leaky_re_lu_13[0][0]

____________________________________________________________________________________________________

leaky_re_lu_19 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_19[0][0]

____________________________________________________________________________________________________

batch_normalization_21 (BatchNor (None, 38, 38, 64)    256         conv2d_21[0][0]

____________________________________________________________________________________________________

conv2d_20 (Conv2D)               (None, 19, 19, 1024)  9437184     leaky_re_lu_19[0][0]

____________________________________________________________________________________________________

leaky_re_lu_21 (LeakyReLU)       (None, 38, 38, 64)    0           batch_normalization_21[0][0]

____________________________________________________________________________________________________

batch_normalization_20 (BatchNor (None, 19, 19, 1024)  4096        conv2d_20[0][0]

____________________________________________________________________________________________________

space_to_depth_x2 (Lambda)       (None, 19, 19, 256)   0           leaky_re_lu_21[0][0]

____________________________________________________________________________________________________

leaky_re_lu_20 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_20[0][0]

____________________________________________________________________________________________________

concatenate_1 (Concatenate)      (None, 19, 19, 1280)  0           space_to_depth_x2[0][0]

                                                                   leaky_re_lu_20[0][0]

____________________________________________________________________________________________________

conv2d_22 (Conv2D)               (None, 19, 19, 1024)  11796480    concatenate_1[0][0]

____________________________________________________________________________________________________

batch_normalization_22 (BatchNor (None, 19, 19, 1024)  4096        conv2d_22[0][0]

____________________________________________________________________________________________________

leaky_re_lu_22 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_22[0][0]

____________________________________________________________________________________________________

conv2d_23 (Conv2D)               (None, 19, 19, 425)   435625      leaky_re_lu_22[0][0]

====================================================================================================

Total params: 50,983,561

Trainable params: 50,962,889

Non-trainable params: 20,672

　　

2、输入输出数据类型

（1）输入数据：(m, 608, 608, 3)

（2）输出数据：(m, 19, 19, 5, 85)

3、检测过程

（1）Score-thresholding：throw away boxes that have detected a class with a score less than the threshold（0.4）

（2）Non-max suppression: Compute the Intersection over Union and avoid selecting overlapping boxes

  • Select the box that has the highest score.
  • Compute its overlap with all other boxes, and remove boxes that overlap it more than iou_threshold.
  • Go back to step 1 and iterate until there's no more boxes with a lower score than the current selected box.

This will remove all boxes that have a large overlap with the selected boxes. Only the "best" boxes remain.

4、总结

    • YOLO is a state-of-the-art object detection model that is fast and accurate
    • It runs an input image through a CNN which outputs a 19x19x5x85 dimensional volume.
    • The encoding can be seen as a grid where each of the 19x19 cells contains information about 5 boxes.
    • You filter through all the boxes using non-max suppression. Specifically:
      • Score thresholding on the probability of detecting a class to keep only accurate (high probability) boxes
      • Intersection over Union (IoU) thresholding to eliminate overlapping boxes
    • Because training a YOLO model from randomly initialized weights is non-trivial and requires a large dataset as well as lot of computation, we used previously trained model parameters in this exercise. If you wish, you can also try fine-tuning the YOLO model with your own dataset, though this would be a fairly non-trivial exercise.

项目总结三：目标检测项目（Car detection with YOLOv2）的更多相关文章

  1. 明火烟雾目标检测项目部署（YoloV5+Flask）

    明火烟雾目标检测项目部署 目录 明火烟雾目标检测项目部署 1. 拉取Docker PyToch镜像 2. 配置项目环境 2.1 更换软件源 2.2 下载vim 2.3 解决vim中文乱码问题 3. 运 ...

  2. 多尺度目标检测 Multiscale Object Detection

    多尺度目标检测 Multiscale Object Detection 我们在输入图像的每个像素上生成多个锚框.这些定位框用于对输入图像的不同区域进行采样.但是,如果锚定框是以图像的每个像素为中心生成 ...

  3. 目标检测--Scalable Object Detection using Deep Neural Networks(CVPR 2014)

    Scalable Object Detection using Deep Neural Networks 作者: Dumitru Erhan, Christian Szegedy, Alexander ...

  4. 吴恩达《深度学习》第四门课（3）目标检测（Object detection）

    3.1目标定位 (1)案例1:在构建自动驾驶时,需要定位出照片中的行人.汽车.摩托车和背景,即四个类别.可以设置这样的输出,首先第一个元素pc=1表示有要定位的物体,那么用另外四个输出元素表示定位框的 ...

  5. 目标检测 - Tensorflow Object Detection API

    一. 找到最好的工具 "工欲善其事,必先利其器",如果你想找一个深度学习框架来解决深度学习问题,TensorFlow 就是你的不二之选,究其原因,也不必过多解释,看过其优雅的代码架 ...

  6. 基于深度学习的目标检测（object detection）—— rcnn、fast-rcnn、faster-rcnn

    模型和方法: 在深度学习求解目标检测问题之前的主流 detection 方法是,DPM(Deformable parts models), 度量与评价: mAP:mean Average Precis ...

  7. spring boot快速入门 1 ：创建项目、 三种启动项目方式

    准备工作: (转载)IDEA新建项目时,没有Spring Initializr选项 最近开始使用IDEA作为开发工具,然后也是打算开始学习使用spring boot. 看着博客来进行操作上手sprin ...

  8. 目标检测（一）RCNN--Rich feature hierarchies for accurate object detection and semantic segmentation(v5)

    作者:Ross Girshick,Jeff Donahue,Trevor Darrell,Jitendra Malik 该论文提出了一种简单且可扩展的检测算法,在VOC2012数据集上取得的mAP比当 ...

  9. 关于目标检测 Object detection

    NO1.目标检测 (分类+定位) 目标检测(Object Detection)是图像分类的延伸,除了分类任务,还要给定多个检测目标的坐标位置.      NO2.目标检测的发展 R-CNN是最早基于C ...

随机推荐

  1. N2N windows下编译安装文件

    n2n安装 n2n原理编译版下载,可直接使用:windows下vpn客户端 n2n_v2_linux_x64 n2n_v2_Win32TAP网卡驱动 #linux环境编译yum install -y ...

  2. centos 7.3 安装配置python3.6.1

    1.先安装一些我遇到的依赖问题(如果有依赖问题按提示安装): yum install xz gcc zlib zlib-devel 2.官网下载源码包 地址:https://www.python.or ...

  3. 【转】Android总结篇系列：Activity Intent Flags及Task相关属性

    [转]Android总结篇系列:Activity Intent Flags及Task相关属性 同上文一样,本文主要引用自网上现有博文,并加上一些自己的理解,在此感谢原作者. 原文地址: http:// ...

  4. 记录mysql安装过程遇到问题

    1. 远程连接授权 登陆mysql数据库    (如果安装在系统盘可以直接命令, 否则要切换到安装目录..bin/) mysql -u root -p mysql> use mysql;   - ...

  5. Linux---一级/二级目录以及位置目录名/指令

    home目录:普通用户登录进来以后的初始位置(会在home目录下创建一个登录名相同的目录例如  / home / 用户名),如果是超级用户则就是 在根目录 /下的 root目录(也就是 /root) ...

  6. flink引出的kafka不同版本的兼容性

    参考: 官网协议介绍:http://kafka.apache.org/protocol.html#The_Messages_Fetch kafka协议兼容性  http://www.cnblogs.c ...

  7. WindowsPE权威指南 第二章 小工具 pedump代码的C语言实现

    2016-11-16 16:29:07 主程序代码 pedump.c #include <windows.h> #include <Richedit.h> #include & ...

  8. spring 5.1.2 mvc RequestMappingHandlerMapping 源码初始化过程

    RequestMappingHandlerMapping getMappingForMethod RequestMappingHandlerMapping 继承于 AbstractHandlerMet ...

  9. 20145232韩文浩 《网络对抗技术》 Web安全基础实践

    问题回答 SQL注入攻击原理?如何防御? 原理:SQL注入攻击指的是通过构建特殊的输入作为参数传入Web应用程序,而这些输入大都是SQL语法里的一些组合,通过执行SQL语句进而执行攻击者所要的操作,使 ...

  10. android-audioRecord

    android 录音功能 录音的大致流程,流程图可以在文件下载:mediarecord.vsdx 切换设备.谁去更新播放流,自动选择新的设备?流程?