lxtGH/CycleMLP

CycleMLP: A MLP-like Architecture for Dense Prediction (ICLR 2022 Oral)

This is a PyTorch implementation of the paper CycleMLP: A MLP-like Architecture for Dense Prediction.

Updates

(29/01/2022) CycleMLP is accepted by ICLR 2022 as an oral presentation.:fire::fire::fire:
(22/07/2021) Initial release.

Model Zoo

We provide CycleMLP models pretrained on ImageNet 2012.

Model	Parameters	FLOPs	Top 1 Acc.	Download
CycleMLP-B1	15M	2.1G	78.9%	model
CycleMLP-B2	27M	3.9G	81.6%	model
CycleMLP-B3	38M	6.9G	82.4%	model
CycleMLP-B4	52M	10.1G	83.0%	model
CycleMLP-B5	76M	12.3G	83.2%	model

Usage

Install

PyTorch 1.7.0+ and torchvision 0.8.1+
timm:

pip install 'git+https://github.com/rwightman/pytorch-image-models@c2ba229d995c33aaaf20e00a5686b4dc857044be'

or

git clone https://github.com/rwightman/pytorch-image-models
cd pytorch-image-models
git checkout c2ba229d995c33aaaf20e00a5686b4dc857044be
pip install -e .

fvcore (optional, for FLOPs calculation)
mmcv, mmdetection, mmsegmentation (optional)

Data preparation

Download and extract ImageNet train and val images from http://image-net.org/. The directory structure is:

│path/to/imagenet/
├──train/
│  ├── n01440764
│  │   ├── n01440764_10026.JPEG
│  │   ├── n01440764_10027.JPEG
│  │   ├── ......
│  ├── ......
├──val/
│  ├── n01440764
│  │   ├── ILSVRC2012_val_00000293.JPEG
│  │   ├── ILSVRC2012_val_00002138.JPEG
│  │   ├── ......
│  ├── ......

Evaluation

To evaluate a pre-trained CycleMLP-B5 on ImageNet val with a single GPU run:

python main.py --eval --model CycleMLP_B5 --resume path/to/CycleMLP_B5.pth --data-path /path/to/imagenet

Training

To train CycleMLP-B5 on ImageNet on a single node with 8 gpus for 300 epochs run:

python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model CycleMLP_B5 --batch-size 128 --data-path /path/to/imagenet --output_dir /path/to/save

Acknowledgement

This code is based on DeiT and pytorch-image-models. Thanks for their wonderful works

Citing

@inproceedings{
chen2022cyclemlp,
title={Cycle{MLP}: A {MLP}-like Architecture for Dense Prediction},
author={Shoufa Chen and Enze Xie and Chongjian GE and Runjian Chen and Ding Liang and Ping Luo},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=NMEceG4v69Y}
}

License

CycleMLP is released under MIT License.

lxtGH / CycleMLP