Coder Social home page Coder Social logo

agjayant / caffe-person-reid Goto Github PK

View Code? Open in Web Editor NEW
62.0 62.0 31.0 9.4 MB

Person Re-Identification: Multi-Task Deep CNN with Triplet Loss

License: Other

CMake 2.41% Makefile 0.53% C++ 64.39% Cuda 3.66% MATLAB 0.78% M 0.01% Python 7.95% Jupyter Notebook 18.80% Shell 0.27% Protocol Buffer 1.21%

caffe-person-reid's People

Contributors

agjayant avatar xiaolonw avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

statml yengjie2200 kevin35day yemika newzhx myles-zmy zysjtu chunfeima huanglizhi chenbangfeng walkoncross xuyunlu1030 sophiezhou winper001 yaokeepmoving zbxzc35 sillytheif december-boy choiyeren zouliangyu shaoxq jealous1989 zhenxingsh aiaini66 afcarl xiezhihua001 sunjunlishi kewenjing1020 yuanwei0908 pandinosaurus xwj8866

caffe-person-reid's Issues

how to name the pictures?

Hi,
I am studying your project recnetly,
I want to train my own data on your net ,
however, I'm confused about the rule to name the pictures.
Because of this ,I am not sure the form of trainlist.txt.
Can you share your list with us?
thanks!

the loss is 0 when I train the model using your code

Hi, @agjayant when I train the model using your solver and model prototxt file by my data. The loss is 0 at the begining. I am not sure it is right.

I0816 16:21:20.639792 24829 solver.cpp:590] Iteration 2560, lr = 0.001
I0816 16:21:23.234153 24829 solver.cpp:243] Iteration 2580, loss = 0
I0816 16:21:23.234200 24829 solver.cpp:590] Iteration 2580, lr = 0.001
I0816 16:21:25.816555 24829 solver.cpp:243] Iteration 2600, loss = 0
I0816 16:21:25.816591 24829 solver.cpp:590] Iteration 2600, lr = 0.001
I0816 16:21:28.449795 24829 solver.cpp:243] Iteration 2620, loss = 0
I0816 16:21:28.449837 24829 solver.cpp:590] Iteration 2620, lr = 0.001
I0816 16:21:31.028082 24829 solver.cpp:243] Iteration 2640, loss = 0

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.