Home

Awesome

AS-MLP architecture for Image Classification

This repo is the official implementation of our ICLR2022 paper "AS-MLP: An Axial Shifted MLP Architecture for Vision" (arXiv).

Model Zoo

Image Classification on ImageNet-1K

NetworkResolutionTop-1 (%)ParamsFLOPsThroughput (image/s)model
AS-MLP-T224x22481.328M4.4G1047onedrive
AS-MLP-S224x22483.150M8.5G619onedrive
AS-MLP-B224x22483.388M15.2G455onedrive

Usage

Install

git clone https://github.com/svip-lab/AS-MLP
cd AS-MLP

conda create -n asmlp python=3.7 -y
conda activate asmlp

conda install pytorch==1.7.1 torchvision==0.8.2 cudatoolkit=10.1 -c pytorch

pip install timm==0.3.2

pip install cupy-cuda101

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

pip install opencv-python==4.4.0.46 termcolor==1.1.0 yacs==0.1.8
<!-- ### Data preparation We use standard ImageNet dataset, you can download it from http://image-net.org/. We provide the following two ways to load data: - For standard folder dataset, move validation images to labeled sub-folders. The file structure should look like: ```bash $ tree data imagenet ├── train │ ├── class1 │ │ ├── img1.jpeg │ │ ├── img2.jpeg │ │ └── ... │ ├── class2 │ │ ├── img3.jpeg │ │ └── ... │ └── ... └── val ├── class1 │ ├── img4.jpeg │ ├── img5.jpeg │ └── ... ├── class2 │ ├── img6.jpeg │ └── ... └── ... ``` -->

Evaluation

To evaluate a pre-trained AS-MLP on ImageNet val, run:

bash train_scripts/test.sh

Training from scratch

To train a AS-MLP on ImageNet from scratch, run:

bash train_scripts/train.sh

You can easily reproduce our results. Enjoy!

Throughput

To measure the throughput, run:

bash train_scripts/get_throughput.sh

Citation

If this project is helpful for you, you can cite our paper:

@InProceedings{Lian_2021_ASMLP,
	title={AS-MLP: An Axial Shifted MLP Architecture for Vision},
	author={Lian, Dongze and Yu, Zehao and Sun, Xing and Gao, Shenghua},
	booktitle={International Conference on Learning Representations (ICLR)},
	year={2022}
}

Other Links

Object Detection and Instance Segmentation: See AS-MLP for Object Detection.

Semantic Segmentation: See AS-MLP for Semantic Segmentation.

Acknowledgement

The code is built upon Swin-Transformer, the cuda kernel is modified from Involution.