keras-sparsity-pattern 0.1.0

sparsity patterns for tensorflow.sparse

keras-sparsity-pattern

Tensorflow2/Keras wrapper for sparsity-pattern package.

Installation

The keras-sparsity-pattern git repo is available as PyPi package

pip install keras-sparsity-pattern
pip install git+ssh://[e-mail]/ulf1/keras-sparsity-pattern.git

Usage

The block-diagonal pattern for tensorflow

import keras_sparsity_pattern
import tensorflow as tf

n_rows, n_cols = 10, 12
mat_pattern = keras_sparsity_pattern.get('block', min(n_rows, n_cols), block_sizes=[3, 1, 2])
mat_values = range(1, len(mat_pattern)+1)

mat = tf.sparse.SparseTensor(
    dense_shape=(n_rows, n_cols),
    indices=mat_pattern,
    values=mat_values)

print(tf.sparse.to_dense(mat))

Please, check the howto.ipynb of the sparsity-pattern package for more sparsity patterns. The .get method works exactly the same.

Appendix

Install a virtual environment

python3.6 -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 Tests: pytest
• 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.