Metadata-Version: 2.1
Name: foscat
Version: 1.1.2
Summary: Synthesise 2D or Healpix data using Cross Scattering Transform
Home-page: https://gitlab.ifremer.fr/deepsee/foscat
Author: Jean-Marc DELOUIS
Author-email: jean.marc.delouis@ifremer.fr
Maintainer: Theo Foulquier
Maintainer-email: theo.foulquier@ifremer.fr
License: MIT
Keywords: Scattering transform,Component separation,denoising
Description-Content-Type: text/markdown
Requires-Dist: imageio
Requires-Dist: imagecodecs
Requires-Dist: matplotlib
Requires-Dist: numpy
Requires-Dist: tensorflow-gpu
Requires-Dist: healpy

Synthesise data (2D or Healpix) using Cross Scattering Transform (https://arxiv.org/abs/2207.12527) usable for component separation (e.g. denoising).
#startup
To generate test files run the follosing lines in python:
>python

>> import foscat.build_demo as dem
>> dem.genDemo()
>> quit()
#run 2D test
>python test2D.py

to plot the corresponding results:

>python test2Dplot.py

#run spherical test

>python testHealpix.py

to plot the corresponding results:

>python testHplot.py

Note: If mpi is available you can run testHealpix_mpi.py that uses 3 nodes to do the same computation than testHealpix.py.
