https://github.com/piiswrong/dec

https://github.com/piiswrong/dec

Last synced: 6 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/piiswrong/dec
• Owner: piiswrong
• License: mit
• Created: 2015-11-19T05:52:13.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2019-12-01T18:38:42.000Z (almost 5 years ago)
• Last Synced: 2024-08-03T04:05:44.390Z (4 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 62.9 MB
• Stars: 454
• Watchers: 18
• Forks: 138
• Open Issues: 19
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ocr - Deep Embedded Clustering for OCR based on caffe

README

        
# Deep Embedded Clustering

This package implements the algorithm described in paper "Unsupervised Deep Embedding for Clustering Analysis". It depends on opencv, numpy, scipy and Caffe.

This implementation is intended for reproducing the results in the paper. If you only want to try the algorithm and find caffe too difficault to install, there is an easier to use experimental implementation in MXNet: https://github.com/dmlc/mxnet/blob/master/example/dec/dec.py, but note that results can be different from the paper. MXNet is a flexible deep learning library with fewer dependencies. You are welcome to try it. Installation guide can be found here: https://mxnet.readthedocs.org/en/latest/build.html. Once you install MXNet, simple go into directory examples/dec and run `python dec.py`.

## Usage

To run, please first build our custom version of Caffe included in this package following the official guide: http://caffe.berkeleyvision.org/installation.html. 

Then download the data set you want to experiment on. We provide scripts for downloading the datasets used in the paper. For example you can download MNIST by `cd mnist; ./get_data.sh`. Once download completes, run `cd dec; python make_mnist_data.py` to prepare data for Caffe.

After data is ready, run `python dec.py DB` to run experiment on with DB. DB can be one of mnist, stl, reutersidf10k, reutersidf. We provide pretrained autoencoder weights with this package. You can use dec/pretrain.py to train your own autoencoder. Please read source for usage info.

### Docker

A Dockerfile has been provided to create a sterile development environment easily.  To build the environment, run `docker build --rm -t dec .` and then `docker run --rm -it dec bash` to shell into the running container.  Alternatively, [nvidia-docker](https://github.com/NVIDIA/nvidia-docker) can be used to enable GPU capability.