(unofficial) - customized fork of DETR, optimized and tuned for intelligent obj detection on 'real world' custom datasets

This is a customized framework based on FB AI's DETR, but with a number of improvements/modifications to optimize it for obj detection on your own datasets. I had started a colab to show how to do this, but with more and more customizations piling up requiring more and more code modifications to DETR core...it became clear building a codebase focused on handling custom datasets would be better and faster for all. Thus, Thunder-Detr was born, 8/1/2020.

Updates: 8/22/20 - add thunder_file_utils.py. Adds a coco_compressor to remap category_ids to contiguous values and rebase to zero. Adds a show_catids to view the categories in a json file and shows the proper "num_classes" value for training DETR with. Usage: