Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/si-cim/protoflow
ProtoFlow is a TensorFlow-based Python toolbox for bleeding-edge research in prototype-based machine learning algorithms.
https://github.com/si-cim/protoflow
lvq machine-learning-algorithms python-toolbox tensorflow
Last synced: 5 days ago
JSON representation
ProtoFlow is a TensorFlow-based Python toolbox for bleeding-edge research in prototype-based machine learning algorithms.
- Host: GitHub
- URL: https://github.com/si-cim/protoflow
- Owner: si-cim
- License: mit
- Created: 2020-01-27T09:20:50.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2023-05-22T22:48:26.000Z (over 1 year ago)
- Last Synced: 2024-10-08T10:12:16.715Z (about 1 month ago)
- Topics: lvq, machine-learning-algorithms, python-toolbox, tensorflow
- Language: Python
- Homepage: https://www.protoflow.ml/en/latest/
- Size: 577 KB
- Stars: 4
- Watchers: 4
- Forks: 2
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ProtoFlow: Prototype Learning in TensorFlow
[](https://travis-ci.org/si-cim/protoflow)
[](https://github.com/si-cim/protoflow/releases)
[](https://protoflow.readthedocs.io/en/latest/?badge=latest)
[](https://pypi.org/project/protoflow/)
[](https://codecov.io/gh/si-cim/protoflow)
[](https://github.com/si-cim/protoflow/blob/master/LICENSE)
**This project is no longer actively maintained**. Please consider using
[ProtoTorch](https://github.com/si-cim/prototorch) instead.
## Description
This is a Python toolbox brewed at the Mittweida University of Applied Sciences
in Germany for bleeding-edge research in Prototype-based Machine Learning
methods and other interpretable models. The focus of ProtoFlow is ease-of-use,
extensibility and speed.
## Installation
ProtoFlow can be easily installed using `pip`. To install the latest version, run
```
pip install -U protoflow
```
To also install the extras, run
```bash
pip install -U protoflow[all]
```
*Note: If you're using [ZSH](https://www.zsh.org/), the square brackets `[ ]`
have to be escaped like so: `\[\]`, making the install command `pip install -U
prototorch\[all\]`.*
To install the bleeding-edge features and improvements before they are release on PyPI, run
```bash
git clone https://github.com/si-cim/protoflow.git
cd protoflow
git checkout dev
pip install -e .[all]
```
For gpu support, additionally run
```bash
pip install -U protoflow[gpu]
```
or simply install `tensorflow-gpu` manually.
## Documentation
The documentation is available at . Should
that link not work try .
## Usage
### For researchers
ProtoFlow is modular. It is very easy to use the modular pieces provided by
ProtoFlow, like the layers, losses, callbacks and metrics to build your own
prototype-based(instance-based) models. These pieces blend-in seamlessly with
Keras allowing you to mix and match the modules from ProtoFlow with other Keras
modules.
### For engineers
ProtoFlow comes prepackaged with many popular Learning Vector Quantization
(LVQ)-like algorithms in a convenient API. If you would simply like to be able
to use those algorithms to train large ML models on a GPU, ProtoFlow lets you do
this without requiring a black-belt in high-performance Tensor computation.
## Bibtex
If you would like to cite the package, please use this:
```bibtex
@misc{Ravichandran2020a,
author = {Ravichandran, J},
title = {ProtoFlow},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/si-cim/protoflow}}
}