2020-02-17 17:00:12 +00:00
|
|
|
# ProtoTorch
|
|
|
|
|
|
|
|
|
|
ProtoTorch is a PyTorch-based Python toolbox for bleeding-edge research in
|
|
|
|
|
prototype-based machine learning algorithms.
|
|
|
|
|
|
2020-04-06 16:48:02 +00:00
|
|
|
[](https://badge.fury.io/gh/si-cim%2Fprototorch)
|
|
|
|
|
[](https://badge.fury.io/py/prototorch)
|
2020-04-06 15:42:29 +00:00
|
|
|
|
2020-04-06 16:07:15 +00:00
|
|
|
[](https://codecov.io/gh/si-cim/prototorch)
|
2020-04-06 17:59:52 +00:00
|
|
|
[](https://pepy.tech/project/prototorch)
|
|
|
|
|
[](https://github.com/si-cim/prototorch/blob/master/LICENSE)
|
2020-02-17 17:00:12 +00:00
|
|
|
|
|
|
|
|
## Description
|
|
|
|
|
|
|
|
|
|
This is a Python toolbox brewed at the Mittweida University of Applied Sciences
|
|
|
|
|
in Germany for bleeding-edge research in Learning Vector Quantization (LVQ)
|
2020-03-30 11:30:10 +00:00
|
|
|
and potentially other prototype-based methods. Although, there are
|
|
|
|
|
other (perhaps more extensive) LVQ toolboxes available out there, the focus of
|
|
|
|
|
ProtoTorch is ease-of-use, extensibility and speed.
|
2020-02-17 17:00:12 +00:00
|
|
|
|
|
|
|
|
Many popular prototype-based Machine Learning (ML) algorithms like K-Nearest
|
|
|
|
|
Neighbors (KNN), Generalized Learning Vector Quantization (GLVQ) and Generalized
|
2020-03-30 11:30:10 +00:00
|
|
|
Matrix Learning Vector Quantization (GMLVQ) are implemented using the "nn" API
|
2020-02-17 17:00:12 +00:00
|
|
|
provided by PyTorch.
|
|
|
|
|
|
|
|
|
|
## Installation
|
|
|
|
|
|
|
|
|
|
ProtoTorch can be installed using `pip`.
|
|
|
|
|
```
|
|
|
|
|
pip install prototorch
|
|
|
|
|
```
|
|
|
|
|
|
2020-03-30 11:30:10 +00:00
|
|
|
To install the bleeding-edge features and improvements:
|
|
|
|
|
```
|
|
|
|
|
git clone https://github.com/si-cim/prototorch.git
|
|
|
|
|
git checkout dev
|
|
|
|
|
cd prototorch
|
|
|
|
|
pip install -e .
|
|
|
|
|
```
|
|
|
|
|
|
2020-02-17 17:00:12 +00:00
|
|
|
## Usage
|
|
|
|
|
|
|
|
|
|
ProtoTorch is modular. It is very easy to use the modular pieces provided by
|
|
|
|
|
ProtoTorch, like the layers, losses, callbacks and metrics to build your own
|
|
|
|
|
prototype-based(instance-based) models. These pieces blend-in seamlessly with
|
|
|
|
|
numpy and PyTorch to allow you mix and match the modules from ProtoTorch with
|
|
|
|
|
other PyTorch modules.
|
|
|
|
|
|
|
|
|
|
ProtoTorch comes prepackaged with many popular LVQ algorithms in a convenient
|
|
|
|
|
API, with more algorithms and techniques coming soon. If you would simply like
|
|
|
|
|
to be able to use those algorithms to train large ML models on a GPU, ProtoTorch
|
|
|
|
|
lets you do this without requiring a black-belt in high-performance Tensor
|
|
|
|
|
computation.
|
2020-04-06 17:59:52 +00:00
|
|
|
|
|
|
|
|
## Bibtex
|
|
|
|
|
|
|
|
|
|
If you would like to cite the package, please use this:
|
|
|
|
|
```bibtex
|
|
|
|
|
@misc{Ravichandran2020,
|
|
|
|
|
author = {Ravichandran, J},
|
|
|
|
|
title = {ProtoTorch},
|
|
|
|
|
year = {2020},
|
|
|
|
|
publisher = {GitHub},
|
|
|
|
|
journal = {GitHub repository},
|
|
|
|
|
howpublished = {\url{https://github.com/si-cim/prototorch}}
|
|
|
|
|
}
|
