Dataset for: AutoSourceID-FeatureExtractor

This is the dataset used in the paper AutoSourceID-FeatureExtractor (paper) for Training, Test and Validation sets. AutoSourceID-FeatureExtractor (ASID-FE) is an innovative framework that uses deep learning to estimate the flux and sub-pixel centre coordinates of sources in MeerLICHT/BlackGEM images. The two files contain the 34x34 source patches and the associated catalogues. If you use the dataset, please cite the appropriate DOIs. Code available at https://github.com/FiorenSt/AutoSourceID-FeatureExtractor