m.neural_network.apply - GRASS manual

NAME

m.neural_network.apply - Applies a neural network for semantic segmentation.

KEYWORDS

raster, apply, neural network, classification, semantic segmentation

SYNOPSIS

m.neural_network.apply

m.neural_network.apply --help

m.neural_network.apply data_dir=name input_model_path=name [num_classes=integer] output_path=string [--help] [--verbose] [--quiet] [--ui]

Flags:

--help: Print usage summary
--verbose: Verbose module output
--quiet: Quiet module output
--ui: Force launching GUI dialog

Parameters:

data_dir=name [required]: Name of the input data directory containing subfolder with unlabled images; Name of input directory
input_model_path=name [required]: Name of the input model directory; Name of input directory
num_classes=integer: Number of classes for classification (default 2); Default: 2
output_path=string [required]: Name of the output directory

DESCRIPTION
NOTES
EXAMPLES
SEE ALSO
REQUIREMENTS
AUTHORS

DESCRIPTION

m.neural_network.apply applies a locally safed neural network using the segmentation_models.pytorch framework for semantic segmentation to new data set.

A locally safed model is applied by providing a directory with images data_dir, the path where the model is stored input_model_path and specifying the options num_classes. The output is saved to output_path.

NOTES

It is expected that all data lie in the directory structure and naming format as created by m.neural_network.preparedata_part1.

EXAMPLES

  m.neural_network.apply data_dir=path/to/data/apply input_model_path=/path/to/model output_path=path/to/output

REQUIREMENTS

AUTHORS

Victoria-Leandra Brunn, mundialis GmbH & Co. KG

SOURCE CODE

Available at: m.neural_network.apply source code (history)

Accessed: Monday Jul 27 12:25:53 2026