m.neural_network.test - GRASS manual

NAME

m.neural_network.test - Tests a U-Net for a binary tree/ no-tree classification and provides statistical validation parameters.

KEYWORDS

raster, test, neural network, classification

SYNOPSIS

m.neural_network.test

m.neural_network.test --help

m.neural_network.test data_dir=name input_model_path=string [num_classes=integer] [class_names=string] 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 subfolders with test images and masks; Name of input directory
input_model_path=string [required]: Name of the input model directory
num_classes=integer: Number of classes for classification (default 2); Default: 2
class_names=string: Class names (default tree/ no-tree); Default: tree,no tree
output_path=string [required]: Name of the output directory

DESCRIPTION
NOTES
EXAMPLES
SEE ALSO
REQUIREMENTS
AUTHORS

DESCRIPTION

m.neural_network.test tests a neural network using the segmentation_models.pytorch framework for semantic segmentation and provides statistics for quality assessment.

A locally safed model is tested by providing a directory with test images data_dir, the path where the model can be found input_model_path and specifying the options num_classes and class_names. The statistics are 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.test data_dir=path/to/data/train/ 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.test source code (history)

Accessed: Monday Jul 27 12:26:07 2026