my fork of prototorch_models
Go to file
2021-05-03 13:20:49 +02:00
examples Update example script 2021-04-29 19:25:08 +02:00
prototorch/models Add support for multiple optimizers 2021-05-03 13:20:49 +02:00
.gitignore Update gitignore 2021-04-21 14:54:22 +02:00
LICENSE Initial commit 2021-04-21 13:13:28 +02:00
README.md Add more models 2021-04-29 23:37:22 +02:00
setup.py Automatic Formating. 2021-04-23 17:27:47 +02:00

ProtoTorch Models

Pre-packaged prototype-based machine learning models using ProtoTorch and PyTorch-Lightning.

Installation

To install this plugin, simple install ProtoTorch first by following the installation instructions there and then install this plugin by doing:

git clone https://github.com/si-cim/prototorch_models.git && cd prototorch_models
pip install -e .

The plugin should then be available for use in your Python environment as prototorch.models.

Development setup

It is recommended that you use a virtual environment for development. If you do not use conda, the easiest way to work with virtual environments is by using virtualenvwrapper. Once you've installed it with pip install virtualenvwrapper, you can do the following:

export WORKON_HOME=~/pyenvs
mkdir -p $WORKON_HOME
source /usr/local/bin/virtualenvwrapper.sh  # might be different
# source ~/.local/bin/virtualenvwrapper.sh
mkvirtualenv pt
workon pt
git clone git@github.com:si-cim/prototorch_models.git
cd prototorch_models
git checkout dev
pip install -e .[all]  # \[all\] if you are using zsh or MacOS

To assist in the development process, you may also find it useful to install yapf, isort and autoflake. You can install them easily with pip.

Available models

  • GLVQ
  • Siamese GLVQ
  • Neural Gas

Work in Progress

  • CBC
  • LVQMLN
  • GMLVQ
  • Limited-Rank GMLVQ

Planned models

  • Local-Matrix GMLVQ
  • GTLVQ
  • RSLVQ
  • PLVQ
  • SILVQ
  • KNN