ra1ph2/Vision-Transformer

Implementation of Vision Transformer from scratch and performance compared to standard CNNs (ResNets) and pre-trained ViT on CIFAR10 and CIFAR100.

语言：Jupyter Notebook · GitHub 星标：121 · Fork：13

话题：attention-mechanism · computer-vision · convolutional-neural-networks · jupyter-notebook · pytorch · transformer-architecture

在 GitHub 上查看原仓库