Update README.md

This commit is contained in:
blackfly 2020-03-30 13:30:10 +02:00
parent cab2d5e77c
commit 9dca392159

View File

@ -9,14 +9,13 @@ prototype-based machine learning algorithms.
This is a Python toolbox brewed at the Mittweida University of Applied Sciences This is a Python toolbox brewed at the Mittweida University of Applied Sciences
in Germany for bleeding-edge research in Learning Vector Quantization (LVQ) in Germany for bleeding-edge research in Learning Vector Quantization (LVQ)
methods. Although, there are other (perhaps more extensive) LVQ toolboxes and potentially other prototype-based methods. Although, there are
available out there, the focus of ProtoPy is ease-of-use, extensibility and other (perhaps more extensive) LVQ toolboxes available out there, the focus of
speed. ProtoTorch is ease-of-use, extensibility and speed.
Many popular prototype-based Machine Learning (ML) algorithms like K-Nearest Many popular prototype-based Machine Learning (ML) algorithms like K-Nearest
Neighbors (KNN), Generalized Learning Vector Quantization (GLVQ) and Generalized Neighbors (KNN), Generalized Learning Vector Quantization (GLVQ) and Generalized
Matrix Learning Vector Quantization (GMLVQ) including the recent Learning Vector Matrix Learning Vector Quantization (GMLVQ) are implemented using the "nn" API
Quantization Multi-Layer Network (LVQMLN) are implemented using the "nn" API
provided by PyTorch. provided by PyTorch.
## Installation ## Installation
@ -26,6 +25,14 @@ ProtoTorch can be installed using `pip`.
pip install prototorch pip install prototorch
``` ```
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 .
```
## Usage ## Usage
ProtoTorch is modular. It is very easy to use the modular pieces provided by ProtoTorch is modular. It is very easy to use the modular pieces provided by