This paper proposes various techniques that help Vision Transformer (ViT) to learn small-size datasets from scratch successfully. ViT. which applied the transformer structure to the image classification task. has outperformed convolutional neural networks. https://www.bekindtopets.com/flash-grab-Viqua-F4-Ultraviolet-Water-System-Powered-by-UVMax-36-gpm-top-savings/