Educational python for Neural Networks, written in pure Python/NumPy.

Last update: Oct 27, 2022

Overview

EpyNN

EpyNN is written in pure Python/NumPy.

If you use EpyNN in academia, please cite:

Malard F., Danner L., Rouzies E., Meyer J. G., Lescop E., Olivier-Van Stichelen S. EpyNN: Educational python for Neural Networks, 2021, Submitted.

Documentation

Please visit https://epynn.net/ for extensive documentation.

Purpose

EpyNN is intended for teachers, students, scientists, or more generally anyone with minimal skills in Python programming who wish to understand and build from basic implementations of Neural Network architectures.

Although EpyNN can be used for production, it is meant to be a library of homogeneous architecture templates and practical examples which is expected to save an important amount of time for people who wish to learn, teach or develop from scratch.

Content

EpyNN features scalable, minimalistic and homogeneous implementations of major Neural Network architectures in pure Python/Numpy including:

Model and function rules and definition:

While not enhancing, extending or replacing EpyNN's documentation, series of live examples in Python and Jupyter notebook formats are offered online and within the archive, including:

Reliability

EpyNN has been cross-validated against TensorFlow/Keras API and provides identical results for identical configurations in the limit of float64 precision.

Please see Is EpyNN reliable? for details and executable codes.

Recommended install

Linux/MacOS

# Use bash shell
bash

# Clone git repository
git clone https://github.com/Synthaze/EpyNN

# Alternatively, not recommended
# pip3 install EpyNN
# epynn

# Change directory to EpyNN
cd EpyNN

# Install EpyNN dependencies
pip3 install -r requirements.txt

# Export EpyNN path in $PYTHONPATH for current session
export PYTHONPATH=$PYTHONPATH:$PWD

Linux: Permanent export of EpyNN directory path in $PYTHONPATH.

> ~/.bashrc # Source .bashrc to refresh $PYTHONPATH source ~/.bashrc ">

# Append export instruction to the end of .bashrc file
echo "export PYTHONPATH=$PYTHONPATH:$PWD" >> ~/.bashrc

# Source .bashrc to refresh $PYTHONPATH
source ~/.bashrc

MacOS: Permanent export of EpyNN directory path in $PYTHONPATH.

> ~/.bash_profile # Source .bash_profile to refresh $PYTHONPATH source ~/.bash_profile ">

# Append export instruction to the end of .bash_profile file
echo "export PYTHONPATH=$PYTHONPATH:$PWD" >> ~/.bash_profile

# Source .bash_profile to refresh $PYTHONPATH
source ~/.bash_profile

Windows

# Clone git repository
git clone https://github.com/Synthaze/EpyNN

# Alternatively, not recommended
# pip3 install EpyNN
# epynn

# Change directory to EpyNN
chdir EpyNN

# Install EpyNN dependencies
pip3 install -r requirements.txt

# Show full path of EpyNN directory
echo %cd%

Copy the full path of EpyNN directory, then go to: Control Panel > System > Advanced > Environment variable

If you already have PYTHONPATH in the User variables section, select it and click Edit, otherwise click New to add it.

Paste the full path of EpyNN directory in the input field, keep in mind that paths in PYTHONPATH should be comma-separated.

ANSI coloring schemes do work on native Windows10 and later. For prior Windows versions, users should configure their environment to work with ANSI coloring schemes for optimal experience.

Current release

1.0 - Initial release

nnlibs contains API sources.
nnlive contains live examples in Python and Jupyter notebook formats.
https://epynn.net/ contains extensive documentation.

See CHANGELOG.md for past releases.

Project tree

nnlibs

convolution
dense
dropout
embedding
flatten
gru
lstm
pooling
rnn
template
network
commons
- schedule.py
- library.py
- metrics.py
- loss.py
- plot.py
- io.py
- models.py
- logs.py
- maths.py

nnlive

You might also like...

A concept I came up which ditches the idea of "layers" in a neural network.

Dynet A concept I came up which ditches the idea of "layers" in a neural network. Install Copy Dynet.py to your project. Run the example Install matpl

4 Dec 5, 2021

Python library which makes it possible to dynamically mask/anonymize data using JSON string or python dict rules in a PySpark environment.

pyspark-anonymizer Python library which makes it possible to dynamically mask/anonymize data using JSON string or python dict rules in a PySpark envir

6 Jun 30, 2022

learn python in 100 days, a simple step could be follow from beginner to master of every aspect of python programming and project also include side project which you can use as demo project for your personal portfolio

learn python in 100 days, a simple step could be follow from beginner to master of every aspect of python programming and project also include side project which you can use as demo project for your personal portfolio

6 Nov 5, 2022

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

What is xLearn? xLearn is a high performance, easy-to-use, and scalable machine learning package that contains linear model (LR), factorization machin

3k Jan 8, 2023

A modular active learning framework for Python

Comments

update train for images

better to pick first label of each class programmatically otherwise it can change when then set of images changes. In my nb the indexes you had hardcoded were both class 0

opened by jgmeyerucsd 1

Releases(v1.2)

v1.2(Jul 20, 2022)

EpyNN version published in:

Malard F., Danner L., Rouzies E., Meyer J. G., Lescop E., Olivier-Van Stichelen S. EpyNN: Educational python for Neural Networks, SoftwareX 19 (2022).
Source code(tar.gz)
Source code(zip)
1.1(Nov 14, 2021)

Initial release with improvements.
Source code(tar.gz)
Source code(zip)
1.0.4(Sep 17, 2021)

Initial release of EpyNN.
Source code(tar.gz)
Source code(zip)

Educational python for Neural Networks, written in pure Python/NumPy.

Related tags

Overview

EpyNN

Documentation

Purpose

Content

Reliability

Recommended install

Current release

1.0 - Initial release

Project tree

You might also like...

A concept I came up which ditches the idea of "layers" in a neural network.

Python library which makes it possible to dynamically mask/anonymize data using JSON string or python dict rules in a PySpark environment.

learn python in 100 days, a simple step could be follow from beginner to master of every aspect of python programming and project also include side project which you can use as demo project for your personal portfolio

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

A modular active learning framework for Python

A library of extension and helper modules for Python's data analysis and machine learning libraries.

Sequence learning toolkit for Python

Simple structured learning framework for python

Python implementation of the rulefit algorithm

Comments

update train for images

Releases(v1.2)

v1.2(Jul 20, 2022)

1.1(Nov 14, 2021)

1.0.4(Sep 17, 2021)

Owner

Software Engineer Salary Prediction

A python fast implementation of the famous SVD algorithm popularized by Simon Funk during Netflix Prize

Factorization machines in python

Markov bot - A Writing bot based on Markov Chain for Data Structure Lab

Solve automatic numerical differentiation problems in one or more variables.

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

Getting Profit and Loss Make Easy From Binance

ETNA is an easy-to-use time series forecasting framework.

A model to predict steering torque fully end-to-end

Data Efficient Decision Making

Simple Machine Learning Tool Kit

distfit - Probability density fitting

Massively parallel self-organizing maps: accelerate training on multicore CPUs, GPUs, and clusters

Skforecast is a python library that eases using scikit-learn regressors as multi-step forecasters

AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker

A benchmark of data-centric tasks from across the machine learning lifecycle.

LightGBM + Optuna: no brainer

Create large-scale ML-driven multiscale simulation ensembles to study the interactions

A quick reference guide to the most commonly used patterns and functions in PySpark SQL

End to End toy example of MLOps