Looking for help with transfer learning/fine tuning YOLOX

Hello,

I would like to enhance the standard COCO trained YOLOX_tiny model with some additional images from the environment I intend to deploy it in, to improve accuracy and reduce false positives. I have seen tutorials on doing transfer learning/fine tuning on other YOLO variants like Yolov5, where the backbone is frozen, training is done, then backbone is unfrozen and some more training is done with smaller learning rates (fine tuning).

I see that the ability to freeze layers is present in YOLOX, but I haven't been able to find a write up/tutorial on which layers to freeze, what kind of learning parameters to use etc. Any help would be appreciated!

Review YOLOX's existing layer-freezing support and the YOLOX_tiny COCO training setup first. Document which layers and learning parameters are appropriate for transfer learning and fine-tuning, including the freeze/unfreeze sequence, so users can follow a reproducible workflow.