search

microsoft / Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
https://arxiv.org/abs/2103.14030
MIT License
13.72k stars 2.04k forks source link

1k model in the ImageNet-22k pre-trained models? #43

Closed jinwon-samsung closed 3 years ago

jinwon-samsung commented 3 years ago

https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22kto1k.pth\

What does the models under the 1k model column in the ImageNet-22k pre-trained models mean?

Does it mean that it is pre-trained under the Imagent-22k and then trained on the 1k model?

zeliu98 commented 3 years ago

Yes, you are right. And you can find the only 22k pretrained weight from the 22K model column.