https://github.com/alshedivat/adios

ADIOS: Architectures Deep In Output Space
https://github.com/alshedivat/adios

deep-learning keras

Last synced: 14 days ago
JSON representation

ADIOS: Architectures Deep In Output Space

• Host: GitHub
• URL: https://github.com/alshedivat/adios
• Owner: alshedivat
• License: mit
• Created: 2016-05-30T05:14:38.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2018-07-20T14:50:07.000Z (over 6 years ago)
• Last Synced: 2024-10-03T19:24:03.065Z (about 1 month ago)
• Topics: deep-learning, keras
• Language: Python
• Homepage:
• Size: 21.5 KB
• Stars: 6
• Watchers: 3
• Forks: 5
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# ADIOS: Architectures Deep In Output Space

ADIOS is implemented as a thin wrapper around Keras' `Graph` model (i.e., multiple-input multiple-output deep architecture) by adding the adaptive thresholding functionality as described in the paper.

`adios.utils.assemble.assemble` helper function provides and handy way to construct ADIOS and MLP models from config dictionaries.

Configs can be generated from templates using `adios.utils.jobmab.gen_configurations`.

Examples of templates are given in `configs/` folder in YAML format.

Additionally, we provide utility functions for hyperparameter or architecture search using [Jobman](http://deeplearning.net/software/jobman/about.html).

All example scripts are given in `scripts/`.

**Note:** `keras.models.Graph` is no longer supported starting from `keras-v1.0` as of April, 2016.

The current version of ADIOS uses the legacy code, `keras.legacy.models.Graph`.

### Requirements

- `NumPy`

- `pyyaml`

- `Theano`

- `keras>=1.0`

- `scikit-learn`

The requirements can be installed via `pip` as follows:

```bash

$ pip install -r requirements.txt

```

Optional (needed only for using Jobman):

- `argparse`

- [Jobman](http://deeplearning.net/software/jobman/about.html)

### Installation

To use the code, we recommend installing it as Python package in the development mode as follows:

```bash

$ python setup.py develop [--user]

```

The `--user` flag (optional) will install the package for a given user only.

### Other implementations

- [ADIOS implementation](https://github.com/y3nk0/Multi-label-with-Deep-Learning) by [y3nk0](https://github.com/y3nk0).

### Citation

```bibtex

@inproceedings{cisse2016adios,

  title={ADIOS: Architectures Deep In Output Space},

  author={Cisse, Moustapha and Al-Shedivat, Maruan and Bengio, Samy},

  booktitle={Proceedings of The 33rd International Conference on Machine Learning},

  pages={2770-–2779},

  year={2016}

}

```

### License

MIT (for details, please refer to [LICENSE](https://github.com/alshedivat/adios/blob/master/LICENSE))

Copyright (c) 2016-2018 Moustapha Cisse, Maruan Al-Shedivat, Samy Bengio