mmsegmentation/configs/fp16
Junjun2016 18bbad97f8 Fix random behavior of update_model_index in pre-commit hook (#784) 2021-08-15 23:33:08 +08:00
..
README.md comment tag (#505) 2021-04-24 09:58:59 -07:00
deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py [Bug fix] fixed fp16 inference (#497) 2021-04-24 09:57:33 -07:00
deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py [Bug fix] fixed fp16 inference (#497) 2021-04-24 09:57:33 -07:00
fcn_r101-d8_512x1024_80k_fp16_cityscapes.py [Bug fix] fixed fp16 inference (#497) 2021-04-24 09:57:33 -07:00
fp16.yml Fix random behavior of update_model_index in pre-commit hook (#784) 2021-08-15 23:33:08 +08:00
pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py [Bug fix] fixed fp16 inference (#497) 2021-04-24 09:57:33 -07:00

README.md

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

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
FCN R-101-D8 512x1024 80000 5.37 8.64 76.80 - config model | log
PSPNet R-101-D8 512x1024 80000 5.34 8.77 79.46 - config model | log
DeepLabV3 R-101-D8 512x1024 80000 5.75 3.86 80.48 - config model | log
DeepLabV3+ R-101-D8 512x1024 80000 6.35 7.87 80.46 - config model | log