初探DAN
Posted elong1995
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了初探DAN相关的知识,希望对你有一定的参考价值。
file:///C:/Users/elong/AppData/Local/Temp/MarkdownPadPreview.html
D:\\users\\elong\\Anaconda3\\envs\\mini27\\python.exe E:/DeepAlignmentNetwork-master/DeepAlignmentNetwork/DANtesting.py
Loading network...
Input shape: (None, 1, 112, 112)
Network being tested: ..\\DAN.npz
Normalization is set to: corners
Failure threshold is set to: 0.08
Processing common subset of the 300W public test set (test sets of LFPW and HELEN)
Average error: 0.031690109191
Processing challenging subset of the 300W public test set (IBUG dataset)
Average error: 0.0520462443183
Showing results for the entire 300W pulic test set (IBUG dataset, test sets of LFPW and HELEN
Average error: 0.0374315832012
AUC @ 0.08: 0.534141292735
Failure rate: 0.0160256410256
Processing 300W private test set
Average error: 6.04116817062
AUC @ 0.08: 0.155705555556
Failure rate: 0.69
Process finished with exit code 0
以上是关于初探DAN的主要内容,如果未能解决你的问题,请参考以下文章
Dan Abramov(React 核心开发,Redux 作者) 为什么说“再见了 整洁代码”?
WS-DAN 复现 WSDAN(Weakly Supervised Data Augmentation Network)