Giter Site home page Giter Site logo

lirongwu / dcv Goto Github PK

View Code? Open in Web Editor NEW
7.0 2.0 1.0 13 KB

Code for TNNLS paper "Deep Clustering and Visualization for End-to-End High Dimensional Data analysis"

License: MIT License

Python 100.00%
clustering visualization geometric-deep-learning manifold-learning high-dimensional-data

dcv's Introduction

Deep Clustering and Visualization (DCV)

This is a PyTorch implementation of the DCV, and the code includes the following modules:

  • Datasets (MNIST, HAR, USPS, Pendigits, Reuters-10K, Coil100)

  • Training for DCV-encoder and DCV-decoder

  • Visualization

  • Evaluation metrics

Requirements

  • pytorch == 1.6.0

  • scipy == 1.3.1

  • numpy == 1.18.5

  • scikit-learn == 0.21.3

  • umap == 1.18.5

  • networkx == 2.3

Description

  • main.py

    • Train() -- Train a new model
    • Test() -- Test the learned model for evaluating generalization
  • dataloader.py

    • GetData() -- Load data of selected dataset
  • model.py

    • LISV2_MLP() -- model and loss
  • tool.py

    • GIFPloter() -- Auxiliary tool for online plot

    • DataSaver() -- Save intermediate and final results

    • cluster_acc() -- Calculate clustering accuracy

Dataset

The datasets and pretrained models used in this paper are available in:

https://drive.google.com/file/d/19oO9l9WgnPZuqojKFVtwIRFm4s0vcY02/view?usp=sharing

Running the code

  1. Install the required dependency packages
  2. To get the results on a specific dataset, run with proper hyperparameters
python main.py --data_name dataset
  1. To get the data, metrics, and visualisation, refer to
../log/dataset/

where the dataset is one of the six datasets (MNIST, HAR, USPS, Pendigits, Reuters-10K, Coil100)

Citation

If you find this project useful for your research, please use the following BibTeX entry.

@article{wu2022deep,
  title={Deep Clustering and Visualization for End-to-End High-Dimensional Data Analysis},
  author={Wu, Lirong and Yuan, Lifan and Zhao, Guojiang and Lin, Haitao and Li, Stan Z},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2022},
  publisher={IEEE}
}

dcv's People

Contributors

lirongwu avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Forkers

abhisheka456

dcv's Issues

关于运行时间的问题

您好

您的这篇论文非常有意义,并给了我很大的启发.但是在我运行代码时,我对于运行时间有些疑问.

在运行MNIST(70000张图片)时,仅网络初始化计算sigma花了十分钟左右的时间(没有进行后续训练),非常耗时.而论文中,DCV关于MNIST的计算统计时间为18秒左右.所以,您在统计运行时间时,是否将计算sigma的时间包括在内?

希望您能够回答我的疑问,感谢!

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.