DLIB：训练194个地标的Shape_predictor（海伦数据集） [英] DLIB : Training Shape_predictor for 194 landmarks (helen dataset)

问题描述

我正在训练 DLIB 的 shape_predictor ，它使用 helen数据集用于194个面部地标，该数据用于通过<$ c $来检测面部地标dlib库的c> face_landmark_detection_ex.cpp 。

现在，它给了我一个 sp.dat 大约 45 MB 的二进制文件，比给定的文件要少（

与从68个地标获得的结果有很大出入

68个地标图像：

为什么？

解决方案

好吧，看来您还没有阅读代码注释（？）：

  shape_predictor_trainer培训师； 
 //此算法具有许多您可以弄乱的参数。 
 // shape_predictor_trainer的文档说明了所有这些内容。 
 //您还应该阅读Kazemi的论文，其中详细介绍了
 //的所有参数。但是，这里我只是将其中三个
 //设置为其默认值。我这样做是因为我们
 //具有非常小的数据集。特别是，将过采样
 //设置为较高的值（300）可以有效地增加训练集的大小，因此
 //可以帮助该示例。 
 trainer.set_oversampling_amount（300）; 
 //通过显式增加
 //正则化（使nu变小）并使用深度小于
 //的树，我也在减少模型的容量。 
 trainer.set_nu（0.05）; 
 trainer.set_tree_depth（2）; 
  

看看 Kazemi纸，按ctrl -f字符串'parameter'并已阅读...

I am training DLIB's shape_predictor for 194 face landmarks using helen dataset which is used to detect face landmarks through face_landmark_detection_ex.cpp of dlib library.

Now it gave me an sp.dat binary file of around 45 MB which is less compared to file given (http://sourceforge.net/projects/dclib/files/dlib/v18.10/shape_predictor_68_face_landmarks.dat.bz2) for 68 face landmarks. In training

• Mean training error : 0.0203811
• Mean testing error : 0.0204511

and when I used trained data to get face landmarks position, IN result I got..

which are very deviated from the result got from 68 landmarks

68 landmark image:

Why?

解决方案

Ok, looks like you haven't read the code comments (?):

shape_predictor_trainer trainer;
// This algorithm has a bunch of parameters you can mess with.  The
// documentation for the shape_predictor_trainer explains all of them.
// You should also read Kazemi's paper which explains all the parameters
// in great detail.  However, here I'm just setting three of them
// differently than their default values.  I'm doing this because we
// have a very small dataset.  In particular, setting the oversampling
// to a high amount (300) effectively boosts the training set size, so
// that helps this example.
trainer.set_oversampling_amount(300);
// I'm also reducing the capacity of the model by explicitly increasing
// the regularization (making nu smaller) and by using trees with
// smaller depths.  
trainer.set_nu(0.05);
trainer.set_tree_depth(2);

Have a look at the Kazemi paper, ctrl-f the string 'parameter' and have a read...

这篇关于DLIB：训练194个地标的Shape_predictor（海伦数据集）的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！