Skip to main content

ResNeSt

Project description

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

PWC PWC PWC PWC PWC PWC

ResNeSt

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+https://github.com/zhanghang1989/ResNeSt

# 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

Detectron2

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

MMDetection

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 prepare_imagenet.py --download-dir ./

Torch Model

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

Gluon Model

# use resnest50 as an example
cd scripts/gluon/
python verify.py --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

Reference

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

@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}
}

Major Contributors

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

resnest-0.0.6b20221013.tar.gz (36.1 kB view details)

Uploaded Source

Built Distribution

resnest-0.0.6b20221013-py3-none-any.whl (49.0 kB view details)

Uploaded Python 3

File details

Details for the file resnest-0.0.6b20221013.tar.gz.

File metadata

  • Download URL: resnest-0.0.6b20221013.tar.gz
  • Upload date:
  • Size: 36.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.7.14

File hashes

Hashes for resnest-0.0.6b20221013.tar.gz
Algorithm Hash digest
SHA256 eb76f11a90f6e1023b3fe1473ac290fb58e88f31b2ee009a17fb43aa6d9ab098
MD5 9d232bd5796da1e0964020a220cc9ca6
BLAKE2b-256 69f8ea4bf3e39e658402adbf2f1a2745cd625bd37e047b9fb9443f40934b3483

See more details on using hashes here.

File details

Details for the file resnest-0.0.6b20221013-py3-none-any.whl.

File metadata

File hashes

Hashes for resnest-0.0.6b20221013-py3-none-any.whl
Algorithm Hash digest
SHA256 b652dcd246e6d1e69a18f2c2459eed149339094cb65955588f7ada4cf6e3dc84
MD5 d75bee38b8695bf98fabf4e66f4920dd
BLAKE2b-256 3b7a51cfeab4a0abdf4aab0aae813a5ea1e98165be4ec2fc6c66110c676ee41a

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page