【论文阅读】An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

论文链接：AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE ViT：把图像看成 patch token 序列，而不是像素网格或卷积特征图，然后直接用标准Transformer Encoder 做全局建

论文阅读：Attention Is All you Need (Transformer)