rf-detr nano model trained on the following classes, collapsed into one object class: {"Batray","Bird","Boat","Cement_Ship","Egregia","Fish","Jelly","Kayak","Kelp","Mola","Mooring_Buoy","Otter","Person","Pinniped","Secci_Disc","Shark","Surfboard","Velella_velella","Velella_velella_raft","Whale"}
Acts as object detector to feed detection stage of a pipeline
Trained for 20 epochs
metrics
Images, localizations transformed to 640 pixels, 50% overlap
