ResNeSt: Split-Attention Networks
Alternatives To Resnest
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Transformers112,383641,86919 hours ago114July 18, 2023825apache-2.0Python
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stable Diffusion Webui103,367
a day ago2January 17, 20221,516agpl-3.0Python
Stable Diffusion web UI
Pytorch71,0613,3416,72819 hours ago37May 08, 202312,782otherPython
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Keras59,40857819 hours ago80June 27, 202390apache-2.0Python
Deep Learning for humans
Real Time Voice Cloning46,865
a day ago167otherPython
Clone a voice in 5 seconds to generate arbitrary speech in real-time
2 days ago8September 21, 2021227agpl-3.0Python
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Annotated_deep_learning_paper_implementations36,22315 days ago78September 24, 202227mitJupyter Notebook
🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Made With Ml34,182
4 days ago5May 15, 20192mitJupyter Notebook
Learn how to design, develop, deploy and iterate on production-grade ML applications.
Gfpgan32,185913 days ago11September 20, 2022271otherPython
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
21 days ago2February 28, 2022446otherPython
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
Alternatives To Resnest
Select To Compare

Alternative Project Comparisons

PyPI PyPI Pre-release PyPI Nightly Downloads License Unit Test arXiv



Split-Attention Network, A New ResNet Variant. It significantly boosts the performance of downstream models such as Mask R-CNN, Cascade R-CNN and DeepLabV3.

Table of Contents

  1. Pretrained Models
  2. Transfer Learning Models
  3. Verify ImageNet Results
  4. How to Train
  5. Reference

Pypi / GitHub Install

  1. Install this package repo, note that you only need to choose one of the options
# using github url
pip install git+

# using pypi
pip install resnest --pre

Pretrained Models

crop size 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
  • 3rd party implementations are available: Tensorflow, Caffe, JAX.

  • Extra ablation study models are available in link

PyTorch Models

  • Load using Torch Hub
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)
  • Load using python package
# using ResNeSt-50 as an example
from resnest.torch import resnest50
net = resnest50(pretrained=True)

Gluon Models

  • Load pretrained model:
# using ResNeSt-50 as an example
from resnest.gluon import resnest50
net = resnest50(pretrained=True)

Transfer Learning Models


We provide a wrapper for training Detectron2 models with ResNeSt backbone at d2. Training configs and pretrained models are released. See details in d2.


The ResNeSt backbone has been adopted by MMDetection.

Semantic Segmentation

Verify ImageNet Results:

Note: the inference speed reported in the paper are tested using Gluon implementation with RecordIO data.

Prepare ImageNet dataset:

Here we use raw image data format for simplicity, please follow GluonCV tutorial if you would like to use RecordIO format.

cd scripts/dataset/
# assuming you have downloaded the dataset in the current folder
python --download-dir ./

Torch Model

# use resnest50 as an example
cd scripts/torch/
python --model resnest50 --crop-size 224

Gluon Model

# use resnest50 as an example
cd scripts/gluon/
python --model resnest50 --crop-size 224

How to Train

ImageNet Models

Detectron Models

For object detection and instance segmentation models, please visit our detectron2-ResNeSt fork.

Semantic Segmentation


ResNeSt: Split-Attention Networks [arXiv]

Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Zhi Zhang, Haibin Lin, Yue Sun, Tong He, Jonas Muller, R. Manmatha, Mu Li and Alex Smola

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},

Major Contributors

Popular Deep Learning Projects
Popular Pytorch Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Deep Learning