基于Pytorch的Swin Transformer复现，实现在CIFAR10数据集上的训练和分类
采用三个Stage，分别有2、6、2个模块，head分别为3、6、12，经过15次epoch，准确率为72.58%
-
Notifications
You must be signed in to change notification settings - Fork 1
Koorye/swin-transformer
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
基于Pytorch的Swin Transformer复现，实现在CIFAR10数据集上的训练和分类
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published