klxqlehua / dcn Goto Github PK
View Code? Open in Web Editor NEWThis project forked from boyangumn/dcn
This is outdated -- New version: https://github.com/boyangumn/DCN-New
This project forked from boyangumn/dcn
This is outdated -- New version: https://github.com/boyangumn/DCN-New
This is an introduction of the code developed for the Deep Clustering Network (DCN). Please direct your emails to Bo Yang, [email protected] if you have troubles running the code, or find any bugs. Here is the paper: arxiv: https://arxiv.org/pdf/1610.04794v1.pdf Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos and Mingyi Hong "Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering" ============================================== Main files run_rcv1.py : Script to reproduce our results on RCV1 dataset (Table 1). run_20News.py : Script to reproduce our results on 20Newsgroup dataset (Table 2). run_raw_mnist.py : Script to reproduce our results on raw-MNIST dataset (Table 3). run_pre_mnist.py : Script to reproduce our results on pre-processed MNIST dataset (Table 4). run_pendigits.py : Script to reproduce our results on Pendigits dataset (Table 5). multi_layer_km.py : Main file for defining the network, as well as various utility functions. -- More documentations can be found inside each of the above files. -- There are some additional python source files in the repository, which were developed for trying out various ideas. They are kept for possible future use, but are less documented (unfortunately...). ============================================== Data preparation The data file should be named like 'something.pkl.gz', i.e., it should be pickled and compressed by gzip, using python code as follow: """ with gzip.open('something.pkl.gz', 'wb') as f: cPickle.dump([train_x, train_y], f, protocol = 0) """ where train_x and train_y are numpy ndarray with shape train_x: (n_samples, n_features) train_y: (n_samples, ) The path of data files should be made available to the programs by modifying the 'path' local variable in each of the 'run_' python source files. ============================================== Dependencies Theano scikit-learn numpy scipy matplotlib Theanon deep learning tutorial code (can be download from http://deeplearning.net/tutorial/).
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.