安装难度低:执行 pip install vit-pytorch,导入 ViT 后对图像张量执行一次前向计算即可验证成功。
核验依据
GitHub 项目简介: Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
README: For a Pytorch implementation with pretrained models, please see Ross Wightman's repository