This deposit contains the python scripts used for analysing the data produced from the cross-validation experiments conducted for testing and validating a semantic segmentation network. The purpose was to evaluate the suitability of the segmentation network for use in the processing of images from Natural History Collections. The scripts were designed to calculate the results, format data, evaluate the accuracy of the models and generate datasets used for plotting results. The sw_description files (txt and rtf) contain a more detailed description of the three archive files (.zip) included.