Home

Awesome

<div align="center">

PyLaia

PyLaia is a device agnostic, PyTorch based, deep learning toolkit for handwritten document analysis.

It is also a successor to Laia.

Development/Maintenance is now done on Teklia's fork. Please head over there if you want to use the latest version of PyLaia.

Build Coverage Code quality

Python: 3.8+ PyTorch: 1.13.0+ pre-commit: enabled Code style: black

</div>

Get started by having a look at our Wiki!

Several (mostly undocumented) examples of its use are provided at PyLaia-examples.

Installation

In order to install PyLaia, follow this recipe:

git clone https://github.com/jpuigcerver/PyLaia
cd PyLaia
pip install -e .

Please note that the CUDA version of nnutils (nnutils-pytorch-cuda) is installed by default. If you do not have a GPU, you should install the CPU version (nnutils-pytorch).

The following Python scripts will be installed in your system:

Acknowledgments

Work in this toolkit was financially supported by the Pattern Recognition and Human Language Technology (PRHLT) Research Center

BibTeX

@misc{puigcerver2018pylaia,
  author = {Joan Puigcerver and Carlos MocholĂ­},
  title = {PyLaia},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/jpuigcerver/PyLaia}},
  commit = {commit SHA}
}