NAME
m.neural_network.postprocessing.vectorize - Vectorizes classification raster output and clean up results.
KEYWORDS
vector
SYNOPSIS
m.neural_network.postprocessing.vectorize
m.neural_network.postprocessing.vectorize --help
m.neural_network.postprocessing.vectorize [-sc] input=name output=name [rmarea_thres=float] [generalize_thres=float] [--overwrite] [--help] [--verbose] [--quiet] [--ui]
Flags:
- -s
- Apply smoothing
- This smoothes corners which is sometimes not desired
- -c
- Keep corners after generalization (only meaningful for single small tiles)
- Keep corners after the generalization this is only meaningful for single tiles as the training 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:
- input=name [required]
- Input raster classification
- output=name [required]
- Output vector classification
- rmarea_thres=float
- Threshold for cleaning up small areas in square meters
- Default: 5
- generalize_thres=float
- Threshold for generalization/straightening of area border lines
- Default: input raster resolution
m.neural_network.postprocessing.vectorize vectorizes the classification raster output and clean results: remove small areas, if set straighten lines.
Requires GRASS 8.5 for the new
-c flag of
r.to.vect
m.neural_network.postprocessing.vectorize input=classification_patch output=classification_vect
m.neural_network.postprocessing.vectorize input=classification_patch output=classification_vect generalize_thres=0.2
r.to.vect,
Lina Krisztian,
mundialis
SOURCE CODE
Available at:
m.neural_network.postprocessing.vectorize source code
(history)
Accessed: Monday Jul 27 12:26:01 2026
Main index |
Miscellaneous index |
Topics index |
Keywords index |
Graphical index |
Full index
© 2003-2026
GRASS Development Team,
GRASS 8.5.1dev Reference Manual