wujiyang / triplet-loss Goto Github PK
View Code? Open in Web Editor NEWApply triplet loss to face recognition, adding new loss layer to the latest version of caffe.
License: GNU General Public License v2.0
Apply triplet loss to face recognition, adding new loss layer to the latest version of caffe.
License: GNU General Public License v2.0
819375556这是我的qq。有些训练细节还不太明白,能否加Q请教下
@wuyiyang
你好,为什么下面两个分支,求梯度使用的公式不一样呢?
loss=f(a).f(n) - f(a).f(p)
ori_diff = f(n) - f(p)
pos_diff = -f(p)
neg_diff= f(a) 所以loss1的计算没有问题,
那loss2>0时的的算式时怎么来的呢?
谢谢
if(tloss1 > 0)
{
for(int k = 0; k < dim; k ++)
{
fori_diff[k] += (fneg[k] - fpos[k]); // / (pairNum * 1.0 - 2.0);
fpos_diff[k] += -fori[k]; // / (pairNum * 1.0 - 2.0);
fneg_diff[k] += fori[k];
}
}
if(tloss2 > 0)
{
for(int k = 0; k < dim; k ++)
{
fori_diff[k] += -fpos[k]; // / (pairNum * 1.0 - 2.0);
fpos_diff[k] += fneg[k]-fori[k]; // / (pairNum * 1.0 - 2.0);
fneg_diff[k] += fpos[k];
}
}
如题。多谢!
mnist/train/5/00000.png 5
mnist/train/0/00001.png 0
mnist/train/4/00002.png 4
以上为数据输入的train.txt文件
Swish Layer在caffe.proto的相关层和参数都被删了,比如147号让位给了FlipParameter。我加回来以后编译通过。请问为什么一定要删除Swish layer的相关信息?
这样会矛盾吗?以及最终采取slice后取max的步骤,能解释一下吗
作者你好,能给出这样的文件吗,谢谢
Thanks.
@wujiyang 感谢你的分享,我在试着自己训练模型。
我下载的CASIA-WebFace训练集是没有处理过的, 训练前需要做裁剪和对齐处理吗?还是直接用原始图片就可以?
hi. @wujiyang
in face_triplet_train.prototxt
.source: "/media/wujiyang/data/FaceData/train.txt"
I want to know format in train.txt
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.