ViP

Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition, arxiv

PaddlePaddle training/validation code and pretrained models for ViP.

The official and 3rd party pytorch implementation are here.

This implementation is developed by PPViT.

ViP Model Overview

Update

• Update (2022-03-30): Code is refactored.
• Update (2021-11-03): Code and weights are updated.
• Update (2021-09-23): Code is released and ported weights are uploaded.

Models Zoo

Model	Acc@1	Acc@5	#Params	FLOPs	Image Size	Crop_pct	Interpolation	Link
vip_s7	81.48	95.76	25.1M	7.0G	224	0.9	bicubic	google/baidu
vip_m7	82.64	96.12	55.3M	16.4G	224	0.9	bicubic	google/baidu
vip_l7	83.18	96.37	87.8M	24.5G	224	0.875	bicubic	google/baidu

*The results are evaluated on ImageNet2012 validation set.

Note: ViP weights are ported from here

Data Preparation

ImageNet2012 dataset is used in the following file structure:

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

• train_list.txt: list of relative paths and labels of training images. You can download it from: google/baidu
• val_list.txt: list of relative paths and labels of validation images. You can download it from: google/baidu

Usage

To use the model with pretrained weights, download the .pdparam weight file and change related file paths in the following python scripts. The model config files are located in ./configs/.

For example, assume weight file is downloaded in ./vip_s.pdparams, to use the vip_s model in python:

from config import get_config
from vip import build_vip as build_model
# config files in ./configs/
config = get_config('./configs/vip_s.yaml')
# build model
model = build_model(config)
# load pretrained weights
model_state_dict = paddle.load('./vip_s.pdparams')
model.set_state_dict(model_state_dict)

Evaluation

To evaluate model performance on ImageNet2012, run the following script using command line:

sh run_eval_multi.sh

or

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
python main_multi_gpu.py \
-cfg='./configs/vip_s.yaml' \
-dataset='imagenet2012' \
-batch_size=256 \
-data_path='/dataset/imagenet' \
-eval \
-pretrained='./vip_s.pdparams' \
-amp

Note: if you have only 1 GPU, change device number to CUDA_VISIBLE_DEVICES=0 would run the evaluation on single GPU.

Training

To train the model on ImageNet2012, run the following script using command line:

sh run_train_multi.sh

or

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
python main_multi_gpu.py \
-cfg='./configs/vip_s.yaml' \
-dataset='imagenet2012' \
-batch_size=256 \
-data_path='/dataset/imagenet' \
-amp

Note: it is highly recommanded to run the training using multiple GPUs / multi-node GPUs.

Reference

@misc{hou2021vision,
    title={Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition},
    author={Qibin Hou and Zihang Jiang and Li Yuan and Ming-Ming Cheng and Shuicheng Yan and Jiashi Feng},
    year={2021},
    eprint={2106.12368},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}