You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
yexijoe f829d5688e vit_base Ascend910 2 years ago
scripts vit_base Ascend910 2 years ago
src vit_base Ascend910 2 years ago
README_CN.md vit_base Ascend910 2 years ago
eval.py vit_base Ascend910 2 years ago
train.py vit_base Ascend910 2 years ago

Transformer架构已广泛应用于自然语言处理领域。本模型的作者发现,Vision Transformer(ViT)模型在计算机视觉领域中对CNN的依赖不是必需的,直接将其应用于图像块序列来进行图像分类时,也能得到和目前卷积网络相媲美的准确率。

Python Markdown Shell

Contributors (1)