A Discriminative Feature Learning Approach for Deep Face Recognition 的源码部分分析
来源:互联网 发布:嘉兴学院客户端mac 编辑:程序博客网 时间:2024/06/05 05:55
前一篇文章介绍了centerloss的训练过程,以及结果。本文分析一下CenterLoss的源码部分。同时这也是在caffe中添加新的一层的方法。(本文时特例添加loss层)
宏观感受
先来看看作者对一个刚从github上拉下来的caffe做了哪些改动。
step1: 修改caffe.proto
vim caffe/src/caffe/proto/caffe.proto
图为未修改之前LayerParameter的配置
// 1-修改如下注释 //Update the next available ID when you add a new LayerParameter field //LayerParameter next available layer-specific ID: 148 (last added: center_loss_param) //其中148 这个数字得注意。 caffe的LayerParameter中新定义下一个变量的ID:147. 我们新加入一个变量后,下一个新加入的变量ID:148. // 2-添加如下代码 在LayerParameter中 optional CenterLossParameter center_loss_param = 147; // 3-在caffe.proto 最末尾添加自己定义层message CenterLossParameter { optional uint32 num_output = 1; // The number of outputs for the layer optional FillerParameter center_filler = 2; // The filler for the centers optional int32 axis = 3 [default = 1]; //default = 1 相当于c++总的缺省初始化值。 } /* 标签数字1和2,3表示不同的字段在序列化后的二进制数据中的布局位置。在该例中,center_filler字段编码后的数据一定位于num_output后。需要注意的是该值在同一message中不能重复。*/// 说白了,1,2,3代表了他们编码之后的顺序,小号在前,大号在后。
最近一周会更新完毕!!
0 0
- A Discriminative Feature Learning Approach for Deep Face Recognition 的源码部分分析
- A Discriminative Feature Learning Approach for Deep Face Recognition, ECCV16.
- ECCV A Discriminative Feature Learning Approach for Deep Face Recognition
- A Discriminative feature learning approach for deep face recognition
- A Discriminative Feature Learning Approach for Deep Face Recognition
- 阅读A Discriminative Feature Learning Approach for Deep Face Recognition
- A Discriminative Feature Learning Approach for Deep Face Recognition
- 人脸识别 - A Discriminative Feature Learning Approach for Deep Face Recognition
- 人脸识别 - A Discriminative Feature Learning Approach for Deep Face Recognition
- A Discriminative Feature Learning Approach for Deep Face Recognition 原理及在caffe实验复现
- 论文阅读:A Discriminative Feature Learning Approach for Deep Face Recognition
- A Discriminative Feature Learning Approach for Deep Face Recognition 原理及在caffe实验复现
- A Discriminative Feature Learning Approach for Deep Face Recognition 原理及在caffe实验复现
- centerloss系列文章笔记——人脸识别:A Discriminative Feature Learning Approach forDeep Face Recognition
- Discriminative Deep Metric Learning for Face Verification in the Wild(文献泛读)
- 泛读:CVPR2014:Discriminative Deep Metric Learning for Face Verification in theWild
- DeCAF: A deep convolutional activation feature for generic visual recognition
- A New General Deep Learning Approach for Natural Language Processing
- 关于字符串的常用操作 截取substring、分割split、替换replace
- Node.js npm uuid
- 2、web(asp.net):ASP.NET应用程序与页面生命周期
- linux2.6内核SD Card Driver详细解析之一
- 关于西门子PLC中数据类型的使用
- A Discriminative Feature Learning Approach for Deep Face Recognition 的源码部分分析
- bzoj 3683: Falsita 树链剖分+线段树
- Android 自定义View(一)
- AngularJs锚点监听
- 导入数据出错With the Partitioning, OLAP and Data Mining options
- FPGA 学习笔记(十一) VGA驱动的实现
- 简单说一说数据结构——队列
- CCF之图像旋转(java)
- Python中easygui的使用