m.neural_network.postprocessing.patch

NAME

m.neural_network.postprocessing.patch - Patches tiles resulting from neural network inference.

KEYWORDS

SYNOPSIS

m.neural_network.postprocessing.patch

m.neural_network.postprocessing.patch --help

m.neural_network.postprocessing.patch [-b] [tiles_filelist=name] tiles_path=name [edge_cut=integer] [dest_res=float] [area_threshold=float] output=name [--overwrite] [--help] [--verbose] [--quiet] [--ui]

Flags:

-b: No cutting of edges at border tiles
--overwrite: Allow output files to overwrite existing files
--help: Print usage summary
--verbose: Verbose module output
--quiet: Quiet module output
--ui: Force launching GUI dialog

Parameters:

tiles_filelist=name: list of tiles, which should be patched (filename) (if not all files within tiles_path should be used)
tiles_path=name [required]: general path to tiles
edge_cut=integer: edge width of tiles in cells, which will be cut of before patching (tile_overlap of grid); Default: 64
dest_res=float: destination resolution; default is the resolution of the input tiles
area_threshold=float: remove small areas before patching; Default: 0.0005
output=name [required]: patched tiles output; Default: classification_patch

DESCRIPTION
EXAMPLE
- Patch all files within given tiles_path with default edge_cut of 64 (Note: should be half of grid overlap)
SEE ALSO
AUTHORS

DESCRIPTION

m.neural_network.postprocessing.patch patches the tiles (GeoTIFFs) which results from neural network inference.

EXAMPLE

Patch all files within given tiles_path with default edge_cut of 64 (Note: should be half of grid overlap)

m.neural_network.postprocessing.patch tiles_path=/path/to/classification/tifs output=classification_patch

AUTHORS

Lina Krisztian, mundialis

SOURCE CODE

Available at: m.neural_network.postprocessing.patch source code (history)

Accessed: Monday Jul 27 12:26:01 2026