PVTv2

PVTv2: Improved Baselines with Pyramid Vision Transformer, arxiv

PaddlePaddle training/validation code and pretrained models for PVTv2.

The official pytorch implementation is here.

This implementation is developed by PaddleViT.

PVTv2 Model Overview

Update

• Update (2021-09-27): Model FLOPs and # params are uploaded.
• Update (2021-08-11): Code is released and ported weights are uploaded.

Models Zoo

Model	Acc@1	Acc@5	#Params	FLOPs	Image Size	Crop_pct	Interpolation	Link
pvtv2_b0	70.47	90.16	3.7M	0.6G	224	0.875	bicubic	google/baidu(dxgb)
pvtv2_b1	78.70	94.49	14.0M	2.1G	224	0.875	bicubic	google/baidu(2e5m)
pvtv2_b2	82.02	95.99	25.4M	4.0G	224	0.875	bicubic	google/baidu(are2)
pvtv2_b2_linear	82.06	96.04	22.6M	3.9G	224	0.875	bicubic	google/baidu(a4c8)
pvtv2_b3	83.14	96.47	45.2M	6.8G	224	0.875	bicubic	google/baidu(nc21)
pvtv2_b4	83.61	96.69	62.6M	10.0G	224	0.875	bicubic	google/baidu(tthf)
pvtv2_b5	83.77	96.61	82.0M	11.5G	224	0.875	bicubic	google/baidu(9v6n)

*The results are evaluated on ImageNet2012 validation set.

Notebooks

We provide a few notebooks in aistudio to help you get started:

*(coming soon)*

Requirements

• Python>=3.6
• yaml>=0.2.5
• PaddlePaddle>=2.1.0
• yacs>=0.1.8

Data

ImageNet2012 dataset is used in the following folder structure:

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

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 the downloaded weight file is stored in ./pvtv2_b0.pdparams, to use the pvtv2_b0 model in python:

from config import get_config
from pvtv2 import build_pvtv2 as build_model
# config files in ./configs/
config = get_config('./configs/pvtv2_b0.yaml')
# build model
model = build_model(config)
# load pretrained weights, .pdparams is NOT needed
model_state_dict = paddle.load('./pvtv2_b0')
model.set_dict(model_state_dict)

Evaluation

To evaluate PVTv2 model performance on ImageNet2012 with a single GPU, run the following script using command line:

sh run_eval.sh

or

CUDA_VISIBLE_DEVICES=0 \
python main_single_gpu.py \
    -cfg='./configs/pvtv2_b0.yaml' \
    -dataset='imagenet2012' \
    -batch_size=16 \
    -data_path='/dataset/imagenet' \
    -eval \
    -pretrained='./pvtv2_b0'

Run evaluation using multi-GPUs:

sh run_eval_multi.sh

or

CUDA_VISIBLE_DEVICES=0,1,2,3 \
python main_multi_gpu.py \
    -cfg='./configs/pvtv2_b0.yaml' \
    -dataset='imagenet2012' \
    -batch_size=16 \
    -data_path='/dataset/imagenet' \
    -eval \
    -pretrained='./pvtv2_b0'

Training

To train the PVTv2 Transformer model on ImageNet2012 with single GPU, run the following script using command line:

sh run_train.sh

or

CUDA_VISIBLE_DEVICES=0 \
python main_single_gpu.py \
  -cfg='./configs/pvtv2_b0.yaml' \
  -dataset='imagenet2012' \
  -batch_size=16 \
  -data_path='/dataset/imagenet' \

Run training using multi-GPUs:

sh run_train_multi.sh

or

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
python main_multi_gpu.py \
    -cfg='./configs/pvtv2_b0.yaml' \
    -dataset='imagenet2012' \
    -batch_size=32 \
    -data_path='/dataset/imagenet' \

Visualization Attention Map

(coming soon)

Reference

@article{wang2021pvtv2,
  title={Pvtv2: Improved baselines with pyramid vision transformer},
  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
  journal={arXiv preprint arXiv:2106.13797},
  year={2021}
}