pvt.md

PVT

• Paper：Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

• Origin Repo：whai362/PVT

• Code：pvt.py

• Evaluate Transforms：

  # backend: pil
  # input_size: 224x224
  transforms = T.Compose([
      T.Resize(248, interpolation='bicubic'),
      T.CenterCrop(224),
      T.ToTensor(),
      T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
  ])

• Model Details：

  Model	Model Name	Params (M)	FLOPs (G)	Top-1 (%)	Top-5 (%)	Pretrained Model
  PVT-Tiny	pvt_ti	13.2	1.9	74.96	92.47	Download
  PVT-Small	pvt_s	24.5	3.8	79.87	95.05	Download
  PVT-Medium	pvt_m	44.2	6.7	81.48	95.75	Download
  PVT-Large	pvt_l	61.4	9.8	81.74	95.87	Download

• Citation：

  @misc{wang2021pyramid,
      title={Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions}, 
      author={Wenhai Wang and Enze Xie and Xiang Li and Deng-Ping Fan and Kaitao Song and Ding Liang and Tong Lu and Ping Luo and Ling Shao},
      year={2021},
      eprint={2102.12122},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
  }