Mixed Precision Training

Introduction

@article{micikevicius2017mixed,
  title={Mixed precision training},
  author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others},
  journal={arXiv preprint arXiv:1710.03740},
  year={2017}
}

Results and Models on VID task

Method	Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	box AP@50	Config	Download
SELSA	R-50-DC5	pytorch	7e	2.71	-	78.7	config	model | log

Results and Models on MOT task

Method	Detector	ReID	Train Set	Test Set	Public	Inf time (fps)	MOTA	IDF1	FP	FN	IDSw.	Config	Download
Tracktor	R50-FasterRCNN-FPN	R50	half-train	half-val	N	-	64.7	66.6	10710	45270	1152	config	detector | detector_log | reid | reid_log

Results and Models on SOT task

Method	Backbone	Style	Lr schd	Mem (GB)	Inf time (fps)	Success	Norm precision	Config	Download
SiameseRPN++	R-50	-	20e	-	-	49.1	57.0	config	model | log