Git Product home page Git Product logo

ddh's Introduction

ddh

To run this code, you should do the follow things:

1.Download mat-convnet, which is matlab deep learning lib. After that, you should complie it and add path to you project.

2.Extract deep feature,here you can use caffe ,tensorflow and theano etc. with pretrained model to extract feature.

3.Run construct_s.py to construct similarity matrix and some parameters should change in code.You can download cifar-10.mat training data and cifar_KNN.npz from here .

4.Run DDH.m to train network , which will output map and hash codes.

ddh's People

Stargazers

 avatar Guan'an Wang avatar qk avatar Rob Z avatar

Watchers

HT avatar

Forkers

baiyancheng20

ddh's Issues

I retrained on the cifar dataset and got a low map value

Hi,I made my own training set(50000) and test set(10000) on the cifar dataset.The features are extracted from resnet50,I retrained on your code,but I got the low map value.The 16bits is 0.2328.The 32bits is 0.2694.
And do you know why?

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.