* [Enhancement] Change readme style and prepare for metafiles update. * Update apcnet github repo url. * add code snippet. * split code snippet & official repo. * update md2yml hook. * Update metafiles. * Add converted from attribute. * process conflict. * Put defualt variable value. * update bisenet v2 metafile. * checkout to ubuntu environment. * pop empty attribute & make task attribute list. * update readme style * update readme style * update metafiles Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn> |
||
---|---|---|
.. | ||
README.md | ||
deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py | ||
deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py | ||
fcn_r101-d8_512x1024_80k_fp16_cityscapes.py | ||
fp16.yml | ||
pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py |
README.md
Mixed Precision Training
Introduction
Mixed Precision (FP16) Training (ArXiv'2017)
@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 |