geo-deep-learning icon indicating copy to clipboard operation
geo-deep-learning copied to clipboard

Published 20 hours ago • verified publisher icon NRCan

Tiling: replace hdf5 chips to .geotiff and .geojson chips

Open remtav opened this issue 2 years ago • 0 comments

fixes #215 Implements a new script for tiling using the solaris library and replacing the use of patches saved as numpy arrays in HDF5 files. The outputted patches are .tif and .geojson files directly. The .geojson label, once tiled, is then burned to .tif for use with the training script.

The 2 following diagrams are not up to date, but give a general idea of the tiling script's flow and what Tiler class might look light: classes_data_to_tile drawio data_to_tiles_flow drawio

remtav avatar Sep 12 '22 20:09 remtav