khawar-islam / MogaNet

Code release for MogaNet: Efficient Multi-order Gated Aggregation Network

Efficient Multi-order Gated Aggregation Network

This is a PyTorch implementation of MogaNet from our paper:

Efficient Multi-order Gated Aggregation Network
Siyuan Li*, Zedong Wang*, Zicheng Liu, Chen Tan, Haitao Lin, Di Wu, Zhiyuan Chen, Jiangbin Zheng, and Stan Z. Li†. In arXiv, 2022.

We propose MogaNet, a new family of efficient ConvNets, to pursue informative context mining with preferable complexity-performance trade-offs.

Table of Contents

1. Catalog
2. Installation
3. Training
4. Results and Pre-trained Models
   • ImageNet-1K trained models
5. License
6. Acknowledgement

Catalog

We plan to release implementations of MogaNet in a few months. Please watch us for the latest release. Currently, this repo is reimplemented according to our official implementations in OpenMixup, and we are working on cleaning up experimental results and code implementations.

• ImageNet-1K Training Code
• ImageNet-1K Fine-tuning Code
• Downstream Transfer to Object Detection and Instance Segmentation on COCO
• Downstream Transfer to Semantic Segmentation on ADE20K
• Image Classification on Google Colab and Web Demo

Installation

Please check INSTALL.md for installation instructions.

Training

See TRAINING.md for ImageNet-1K training instructions, or refer to our OpenMixup implementations. We have released pre-trained models on OpenMixup in moganet-in1k-weights.

Results and Pre-trained Models

ImageNet-1K trained models

Model	resolution	Params(M)	Flops(G)	Top-1 (%)	Config	Download
MogaNet-XT	224x224	2.97	0.80	76.5	config / script	model / log
MogaNet-T	224x224	5.20	1.10	79.0	config / script	model / log
MogaNet-T	256x256	5.20	1.44	79.6	config / script	model / log
MogaNet-T*	256x256	5.20	1.44	80.0	config / script	model / log
MogaNet-S	224x224	25.3	4.97	83.4	config / script	model / log
MogaNet-B	224x224	43.9	9.93	84.2	config / script	model / log
MogaNet-L	224x224	82.5	15.9	84.6	config / script	model / log

License

This project is released under the Apache 2.0 license.

Acknowledgement

This repository is built using the timm library, DeiT and ConvNeXt repositories.

Citation

If you find this repository helpful, please consider citing:

@article{Li2022MogaNet,
  title={Efficient Multi-order Gated Aggregation Network},
  author={Siyuan Li and Zedong Wang and Zicheng Liu and Cheng Tan and Haitao Lin and Di Wu and Zhiyuan Chen and Jiangbin Zheng and Stan Z. Li},
  journal={ArXiv},
  year={2022},
  volume={abs/2211.03295}
}

(back to top)