Code Monkey home page Code Monkey logo

hrn's Introduction

HRN

Implementation for Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification

Paper

This repo is a implementation for paper Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification that has been accepted by CVPR2022.

Network Architecture

network structure

Visual Demonstration

HMC-LMLP

HMC-LMLP

HMCN

HMCN

C-HMCNN

C-HMCNN

Chang

Chang et al.

Our

Ours

Requirements

  • Python 3.6+
  • Pytorch 1.2+
  • Torchvision 0.4+
  • networkx 2.5
  • CUDA 10.2

Supporting Files for Datasets

Code

hrn's People

Contributors

monsterzhzh avatar

Stargazers

Sawyer Gao avatar Tianlong Ai avatar  avatar supercomπler avatar Ahmed Belgacem avatar WenjingYin avatar  avatar Ldlbest avatar Youren Zhang avatar Lynne Li avatar ZehaoYao avatar li avatar ChenTianhao avatar JIA Shangru avatar UMU689 avatar Liuyong Ding avatar  avatar Ning Wang avatar  avatar  avatar J_JJ avatar Derrick Cai avatar xybh avatar Xinran Wang avatar Eva Feillet avatar  avatar simonweber avatar Zhongyi Zhou avatar  avatar  avatar PeiyuLIU avatar bijan avatar henghui Mo avatar  avatar  avatar Shual avatar Thomas Friedel avatar Chun Chet Ng avatar  avatar Vermillion avatar Bai Bing avatar  avatar 任意 avatar aurae avatar  avatar lemon avatar Lightnessly avatar  avatar rex lau avatar Qi Zhang avatar MianZ avatar

Watchers

James Cloos avatar  avatar

hrn's Issues

关于树的标签定义问题想请教您

self.trees = [ [1,12,35], [2,12,35], [3,12,35], [4,6,9], [5,4,4], [6,4,4], [7,4,4], [8,4,4], [9,8,18], [10,8,18], [11,8,18], [12,8,18], [13,8,18], [14,8,13], [15,8,13], [16,8,13],

这段代码中的标签是如何定义构建的,每个列表中的三个标签分别代表什么意思,他们之间有什么关系吗,想请教您一下,盼解答。

关于联合概率有个疑问想请教您一下

    index = torch.mm(self.stateSpace, fs.T)
    joint = torch.exp(index)

代码中联合概率分布是由网络输出和状态空间矩阵相乘,网络输出在0,1之间,举个例子,状态A为(动物1, 猫1),状态2为(动物1,猫0),那么状态A的联合概率为exp(fs动物+fs猫),状态B的联合概率为exp(fs动物),fs>0,因此状态A的联合概率始终都是大于状态B的。也就说该图是猫的概率始终大于该图是未知类别动物的概率,但实际上应该没有这种先验知识的。
不知道我这么理解对不对,想请教您一下,盼答

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.