---
Model_Info:
   name: "PLSC-ViT"
   description:  "PaddlePaddle 重新实现 Google 官方 Repo 中的 Vision Transformer 算法 《An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale》"
   description_en: "PaddlePaddle reimplementation of Google's repository for the Vision Transformer model that was released with the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale."
   update_time:
   icon: "https://plsc.bj.bcebos.com/assets/modelcenter-icon.png"
   from_repo: "PLSC"
Task:
- tag: 计算机视觉
  tag_en: Computer Vision
  sub_tag: 图像分类
  sub_tag_en: Image Classification
Example:
- tag:
  tag_en:
  sub_tag:
  sub_tag_en:
  title:
  title_en:
  url:
  url_en:
Datasets: ImageNet 1K, ImageNet 21K
Publisher: Baidu
License: Apache 2.0
Paper:
- title: "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale"
  url: https://arxiv.org/abs/2010.11929
IfTraining: 1
IfOnlineDemo: 1