GPU accelerated image processing for everyone

CLIJ2 home


Trains a Weka model using functionality of Fijis Trainable Weka Segmentation plugin.

It takes the given Results Table, sorts its columns alphabetically as extracted features (rows correspond to feature vectors) and a given column name containing the ground truth to train a Weka model. This model will be saved to disc. The given groundTruth column is supposed to be numeric with values 1 represent class 1, value 2 represent class 2 and so on. Value 0 will be ignored for training.

Default values for options are:

Categories: Segmentation, Machine Learning

Availability: Available in Fiji by activating the update sites clij and clij2. This function is part of clijx-weka_-

Usage in ImageJ macro

Ext.CLIJx_trainWekaFromTable(String groundTruthColumnName, String saveModelFilename, Number trees, Number features, Number maxDepth);

Back to CLIJ2 reference Back to CLIJ2 documentation