VOLO: Vision Outlooker for Visual Recognition, arxiv

This is a PyTorch implementation of our paper. We present Vision Outlooker (VOLO). We show that our VOLO achieves SOTA performance on ImageNet and CityScapes. No extra training data is used in our work.

ImageNet top-1 accuracy comparison with the state-of-the-art (sota) CNN-based and Transformer-based models. All results are based on the best test resolutions. Our VOLO-D5 achieves SOTA performance on ImageNet without extra data in 2021/06.

(Updating... codes and models for downstream tasks like semantic segmentation are coming soon.)

Reference

@misc{yuan2021volo,
      title={VOLO: Vision Outlooker for Visual Recognition}, 
      author={Li Yuan and Qibin Hou and Zihang Jiang and Jiashi Feng and Shuicheng Yan},
      year={2021},
      eprint={2106.13112},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

1. Requirements

torch>=1.7.0; torchvision>=0.8.0; timm==0.4.5; tlt==0.1.0; pyyaml; apex-amp

data prepare: ImageNet with the following folder structure, you can extract imagenet by this script.

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

Directory structure in this repo:

│volo/
├──figures/
├──loss/
│  ├── __init__.py
│  ├── cross_entropy.py
├──models/
│  ├── __init__.py
│  ├── volo.py
├──utils/
│  ├── __init__.py
│  ├── utils.py
├──LICENSE
├──README.md
├──distributed_train.sh
├──main.py
├──validate.py

2. VOLO Models

Usage

Instructions on how to use our pre-trained VOLO models:

from models.volo import *
from utils import load_pretrained_weights 

# create model
model = volo_d1()

# load the pretrained weights
# change num_classes based on dataset, can work for different image size 
# as we interpolate the position embeding for different image size.
load_pretrained_weights(model, "/path/to/pretrained/weights", use_ema=False, 
                        strict=False, num_classes=1000)  

3. Validation

To evaluate our VOLO models, run:

python3 validate.py /path/to/imagenet  --model volo_d1 \
  --checkpoint /path/to/checkpoint --no-test-pool --apex-amp --img-size 224 -b 128

Change the --img-size from 224 to 384 or 448 for different image resolution, for example, to evaluate volo-d5 on 512 (87.1), run:

python3 validate.py /path/to/imagenet  --model volo_d5 \
  --checkpoint /path/to/volo_d5_512 --no-test-pool --apex-amp --img-size 512 -b 32

4. Train

Download token labeling data as we use token labeling, details about token labling are in here.

For each VOLO model, we first train it with image-size as 224 then finetune on image-size as 384 or 448/512:

train volo_d1 on 224 and finetune on 384

8 GPU, batch_size=1024, 19G GPU-memory in each GPU with apex-amp (mixed precision training)

train volo_d2 on 224 and finetune on 384

8 GPU, batch_size=1024, 27G GPU-memory in each GPU with apex-amp (mixed precision training)

5. Acknowledgement

We gratefully acknowledge the support of NVIDIA AI Tech Center (NVAITC) to this research project, especially the great helps in GPU technology supports from Terry Jianxiong Yin (NVAITC) and Qingyi Tao (NVAITC).

Related project: T2T-ViT, Token_labeling, pytorch-image-models, official imagenet example

LICENSE

This repo is under the Apache-2.0 license. For commercial use, please contact with the authors.