mmsegmentation/configs/fp16
谢昕辰 725d5aa002 [Feature] support mim (#549)
* dice loss

* format code, add docstring and calculate denominator without valid_mask

* minor change

* restore

* add metafile

* add manifest.in and add config at setup.py

* add requirements

* modify manifest

* modify manifest

* Update MANIFEST.in

* add metafile

* add metadata

* fix typo

* Update metafile.yml

* Update metafile.yml

* minor change

* Update metafile.yml

* add subfix

* fix mmshow

* add more  metafile

* add config to model_zoo

* fix bug

* Update mminstall.txt

* [fix] Add models

* [Fix] Add collections

* [fix] Modify collection name

* [Fix] Set datasets to unet metafile

* [Fix] Modify collection names

* complement inference time
2021-05-31 15:07:24 -07:00
..
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
metafile.yml [Feature] support mim (#549) 2021-05-31 15:07:24 -07:00
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