configs/fp16/README.md

Mixed Precision Training

Introduction

[OTHERS]

@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

Cityscapes

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	download
FCN	R-101-D8	512x1024	80000	5.50	2.66	76.80	-	model | log
PSPNet	R-101-D8	512x1024	80000	5.47	2.68	79.46	-	model | log
DeepLabV3	R-101-D8	512x1024	80000	5.91	1.93	80.48	-	model | log
DeepLabV3+	R-101-D8	512x1024	80000	6.46	2.60	80.46	-	model | log