Skip to content

Latest commit

 

History

History

resnest

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 

README.md

Introduction

Official Repo

Code Snippet

ResNeSt (ArXiv'2020) 
@article{zhang2020resnest,
    title={ResNeSt: Split-Attention Networks},
    author={Zhang, Hang and Wu, Chongruo and Zhang, Zhongyue and Zhu, Yi and Zhang, Zhi and Lin, Haibin and Sun, Yue and He, Tong and Muller, Jonas and Manmatha, R. and Li, Mu and Smola, Alexander},
    journal={arXiv preprint arXiv:2004.08955},
    year={2020}
}

Results

PASCAL VOC

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU Download
FCN ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 77.41% cfg | model | log
PSPNet ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 79.07% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 78.97% cfg | model | log
DeepLabV3plus ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/60 trainaug/val 79.76% cfg | model | log

ADE20k

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU Download
FCN ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 45.74% cfg | model | log
PSPNet ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 46.03% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 46.24% cfg | model | log
DeepLabV3plus ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 46.48% cfg | model | log

CityScapes

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU Download
FCN ImageNet-1k-224x224 S-101-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 78.14% cfg | model | log
PSPNet ImageNet-1k-224x224 S-101-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 78.70% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 79.75% cfg | model | log
DeepLabV3plus ImageNet-1k-224x224 S-101-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/8/220 train/val 80.30% cfg | model | log

More

You can also download the model weights from following sources: