- Note that transformer was saved from https://github.com/wenjtop/transformer.
ViTDemo包含了一个图像分类的模型实例, 基于ViT(Vision Transformer)原理框架
It contains three classifications of different cars images, which are car, motorcycle and train.
用三机动车数据集进行训练和测试
- source from: AI studio
数据集和代码都来源于飞桨
Using ILSVRC2012(imagenet2012) dataset.
使用 ILSVRC2012数据集, 属于imagenet, 专门用于训练图像中的物体识别部分(ImageNet).