ResNeSt
1.0.0
分裂注意網絡,一種新的重新網絡變體。它顯著提高了下游模型的性能,例如蒙版R-CNN,級聯R-CNN和DeepLabV3。

# using github url
pip install git+https://github.com/zhanghang1989/ResNeSt
# using pypi
pip install resnest --pre| 作物大小 | Pytorch | gluon | |
|---|---|---|---|
| Resnest-50 | 224 | 81.03 | 81.04 |
| Resnest-101 | 256 | 82.83 | 82.81 |
| Resnest-200 | 320 | 83.84 | 83.88 |
| Resnest-269 | 416 | 84.54 | 84.53 |
可用第三方實施:Tensorflow,Caffe,Jax。
鏈接中有額外的消融研究模型
import torch
# get list of models
torch . hub . list ( 'zhanghang1989/ResNeSt' , force_reload = True )
# load pretrained models, using ResNeSt-50 as an example
net = torch . hub . load ( 'zhanghang1989/ResNeSt' , 'resnest50' , pretrained = True ) # using ResNeSt-50 as an example
from resnest . torch import resnest50
net = resnest50 ( pretrained = True ) # using ResNeSt-50 as an example
from resnest . gluon import resnest50
net = resnest50 ( pretrained = True )我們為訓練檢測模型提供了包裝紙,並在D2處具有重新骨幹。釋放培訓配置和預告片的模型。請參閱D2中的詳細信息。
MMDetection已採用重新骨幹。
注意:本文中報告的推理速度使用帶有Recordio數據的Gluon實現進行了測試。
在這裡,我們使用原始圖像數據格式為簡單起見,如果您想使用Recordio格式,請關注GluonCV教程。
cd scripts/dataset/
# assuming you have downloaded the dataset in the current folder
python prepare_imagenet.py --download-dir ./ # use resnest50 as an example
cd scripts/torch/
python verify.py --model resnest50 --crop-size 224 # use resnest50 as an example
cd scripts/gluon/
python verify.py --model resnest50 --crop-size 224有關對象檢測和實例細分模型,請訪問我們的destectron2-Resnest fork。
Resnest:分裂注意網絡[ARXIV]
Hang Zhang,Chongruo Wu,Zhongyue Zhang,Yi Zhu,Zhi Zhang,Haibin Lin,Yue Sun,Tong He,Jonas Muller,R。 Manmatha,Mu Li和Alex Smola
@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}
}