The Fermi Large Area Telescope (LAT) has been in orbit of Earth since 2008 collecting gamma rays. One challenge in analyzing LAT data is detecting sources and knowing the various classes of gamma-ray sources and how many there are. Neural networks show impressive accuracy in many fields. Application of these networks to Fermi LAT data can potentially be more successful than traditional statistical methods of source detection. Here we present our attempt at a flexible neural architecture Python package, fermidetect, designed specifically to train and predict on simulated and real Fermi LAT data. This package is based heavily on Meta AI's Detectron2 deep learning framework and will be used to test the performance of different algorithms and hyperparameters on simulated LAT data.