【解释】

tree的两个bounding boxes 都要保留,因为交并比小于0.5;car 0.73保留;pedestrain 0.98保留;motorcycle 0.58保留。一共5个。

【解释】

5个anchor box, 一个anchor box 对应(1+4+20)个标签,所以output volume 是 19*19*5*25

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms的更多相关文章

  1. 课程四(Convolutional Neural Networks),第一周(Foundations of Convolutional Neural Networks) —— 3.Programming assignments:Convolutional Model: application

    Convolutional Neural Networks: Application Welcome to Course 4's second assignment! In this notebook ...

  2. 课程四(Convolutional Neural Networks),第一周(Foundations of Convolutional Neural Networks) —— 2.Programming assignments:Convolutional Model: step by step

    Convolutional Neural Networks: Step by Step Welcome to Course 4's first assignment! In this assignme ...

  3. 课程四(Convolutional Neural Networks),第二 周(Deep convolutional models: case studies) —— 0.Learning Goals

    Learning Goals Understand multiple foundational papers of convolutional neural networks Analyze the ...

  4. 课程四(Convolutional Neural Networks),第二 周(Deep convolutional models: case studies) —— 2.Programming assignments : Keras Tutorial - The Happy House (not graded)

    Keras tutorial - the Happy House Welcome to the first assignment of week 2. In this assignment, you ...

  5. 课程四(Convolutional Neural Networks),第二 周(Deep convolutional models: case studies) ——3.Programming assignments : Residual Networks

    Residual Networks Welcome to the second assignment of this week! You will learn how to build very de ...

  6. 课程四(Convolutional Neural Networks),第一周(Foundations of Convolutional Neural Networks) —— 0.Learning Goals

    Learning Goals Understand the convolution operation Understand the pooling operation Remember the vo ...

  7. 课程四(Convolutional Neural Networks),第二 周(Deep convolutional models: case studies) —— 1.Practice questions

    [解释] 应该是same padding 而不是 valid padding . [解释] 卷积操作用的应该是adding additional layers to the network ,而是应该 ...

  8. 课程四(Convolutional Neural Networks),第一周(Foundations of Convolutional Neural Networks) —— 1.Practice questions:The basics of ConvNets

    [解释] 100*(300*300*3)+ 100=27000100 [解释] (5*5*3+1)*100=7600 [中文翻译] 您有一个输入是 63x63x16, 并 将他与32个滤波器卷积, 每 ...

  9. 课程四(Convolutional Neural Networks),第四 周(Special applications: Face recognition & Neural style transfer) —— 2.Programming assignments:Art generation with Neural Style Transfer

    Deep Learning & Art: Neural Style Transfer Welcome to the second assignment of this week. In thi ...

  10. 课程四(Convolutional Neural Networks),第三 周(Object detection) —— 2.Programming assignments:Car detection with YOLOv2

    Autonomous driving - Car detection Welcome to your week 3 programming assignment. You will learn abo ...

随机推荐

  1. 错误:libstdc++.so.6: wrong ELF class

    1.安装mysql的时候报错缺少GLIBCXX_3.4.15 2.按照网上的下载了libstdc++.so.6.0.17 放到/usr/lib64 下 删除之前的libstdc++.so.6的链接 重 ...

  2. 298. Binary Tree Longest Consecutive Sequence最长连续序列

    [抄题]: Given a binary tree, find the length of the longest consecutive sequence path. The path refers ...

  3. spring 自定义标签的实现

    在我们进行Spring 框架开发中,估计用到最多的就是bean 标签吧,其实在Spring中像<mvc/><context/>这类标签以及在dubbo配置的标签都是属于自定义的 ...

  4. CSS实现左侧多级菜单栏

    首先看要实现的效果, 主要是关心技术实现, 所以没怎么美化 我也是初学html, 所以写的比较啰嗦 1. 使用列表将内容显示出来 <!DOCTYPE html><html>&l ...

  5. c#mysql批量更新的两种方法

    总体而言update 更新上传速度还是慢. 1:  简单的insert  速度稍稍比MySqlDataAdapter慢一点 配合dapper 配置文件 <?xml version="1 ...

  6. JavaScript RegExp.$1

    我们不生产代码 我们只是代码的搬运工 JavaScript RegExp.$1 RegExp 是javascript中的一个内置对象.为正则表达式. RegExp.$1是RegExp的一个属性,指的是 ...

  7. jsp相关笔记(二)

    在jsp中将数据库表格内容读出为一个表格,并在表格中添加超链接: <%@ page language="java" contentType="text/html; ...

  8. No write since last change (add ! to override)

    故障现象: 使用vim修改文件报错,系统提示如下: E37: No write since last change (add ! to override) 故障原因: 文件为只读文件,无法修改. 解决 ...

  9. SpringBoot小新手。

    2018-09-27 最近在学习SpringBoot:教材 先是在https://start.spring.io/下载了工程.demo.zip 下载之后,导入Eclipse工程,pom.xml里面的& ...

  10. deug的使用经验

    最基本的操作是: 1, 首先在一个java文件中设断点,然后运行,当程序走到断点处就会转到debug视图下, 2, F5键与F6键均为单步调试,F5是step into,也就是进入本行代码中执行,F6 ...