https://stats.stackexchange.com/questions/156471/imagenet-what-is-top-1-and-top-5-error-rate

Your classifier gives you a probability for each class. Lets say we had only "cat", "dog", "house", "mouse" as classes (in this order). Then the classifier gives somehting like

0.1; 0.2; 0.0; 0.7

as a result. The Top-1 class is "mouse". The top-2 classes are {mouse, dog}. If the correct class was "dog", it would be counted as "correct" for the Top-2 accuracy, but as wrong for the Top-1 accuracy.

Hence, in a classification problem with kk possible classes, every classifier has 100% top-kkaccuracy. The "normal" accuracy is top-1.

最新文章

  1. 在 Azure HDInsight 中安装和使用 Spark
  2. Markdown 完全指南
  3. 3.2 一般的哈尔空间Vj
  4. Norflash控制器的Verilog建模之一
  5. CAS 4.0.0RC编译环境
  6. Vue.js学习 Item9 – 表单控件绑定
  7. 弹性布局-flex
  8. Android学习第一课
  9. Inline functions
  10. Java异常错误的面试题及答案
  11. 什么样的企业造什么样的软件最easy成功?
  12. linux显示行数命令
  13. messageQ 消息队列
  14. shell编程 之 ssh远程连接
  15. 移动端H5混合开发设置复盘与总结
  16. 看不懂深度Linux系统的文件管理器图标
  17. 10 -- 深入使用Spring -- 5...1 使用Quartz
  18. 一个".java"的源文件中,是否可以包含多个类?(除了匿名内部类),有什么限制?
  19. Codeforces ECR52 div2翻车记
  20. redis之(十二)redis数据的持久化

热门文章

  1. CentOS 7.2 安装zabbix 3.4
  2. Python全栈 项目(电子词典、协程、pdb调试)
  3. scipy 图像处理-深度学习
  4. [ Continuously Update ] The Paper List of Image / Video Captioning
  5. 衡量生活成本:消费者价格指数(CPI, Consumer Price Index)
  6. Alpha发布文案+美工
  7. Python学习之路5 - 函数
  8. WIN8/8.1/10进入BIOS方法图解
  9. 记一次dll强命名冲突事件
  10. loadrunner如何监控windows系统的资源