keras-layernorm-rnn

RNNs with layer normalization


Keywords
keras, layer-normalization, recurrent-neural-network, rnn, rnn-keras, rnn-tensorflow, simplernn, tensorflow
License
MIT
Install
pip install keras-layernorm-rnn==0.2.0

Documentation

Binder Gitpod - Code Now

keras-layernorm-rnn

Table of Contents

Installation

The keras-layernorm-rnn git repo is available as PyPi package

pip install keras-layernorm-rnn
pip install git+ssh://git@github.com/kmedian/keras-layernorm-rnn.git

Usage

Check the examples folder for notebooks.

import tensorflow as tf
from keras_layernorm_rnn import LayernormLSTM3

model = tf.keras.Sequential([
    LayernormLSTM3(units=8, return_sequences=False),  # Many-to-One
    tf.keras.layers.Dense(1, activation='linear')
])

Commands

Install a virtual environment

python3 -m venv .venv
source .venv/bin/activate
pip3 install --upgrade pip
pip3 install -r requirements.txt

(If your git repo is stored in a folder with whitespaces, then don't use the subfolder .venv. Use an absolute path without whitespaces.)

Python commands

  • Jupyter for the examples: jupyter lab
  • Check syntax: flake8 --ignore=F401 --exclude=$(grep -v '^#' .gitignore | xargs | sed -e 's/ /,/g')
  • Run Unit Test: python keras_layernorm_rnn/layernorm_simplernn_test.py
  • Upload to PyPi with twine: python setup.py sdist && twine upload -r pypi dist/*

Clean up

find . -type f -name "*.pyc" | xargs rm
find . -type d -name "__pycache__" | xargs rm -r
rm -r .pytest_cache
rm -r .venv

Support

Please open an issue for support.

Contributing

Please contribute using Github Flow. Create a branch, add commits, and open a pull request.