Open subhankar-ghosh opened 4 years ago
So I concluded that the code, "as is", does not reproduce COCO training from scratch (efficientdet-0).
Here is what I tried:
I concluded that for custom datasets it works, but not for COCO training from scratch for research purposes.
Hi @subhankar-ghosh , by mAP = 2.716, do you mean iou= 0.5:0.95, map = 0.2716? Thank you!
Can anyone please provide the exact settings (hyperparameters, schedulers, optimizer etc) for achieving the SOTA mAP with any of the architectures (D0, D1 etc any of these). With D0 90k training steps Global batch size 16 Number of GPUs 8
I am getting loss: 0.315 mAP = 2.716 small mAP = 0.8 med mAP = 2.59 large mAP = 4.45