Swin Transformer (Swin-T)

This is pretty much state of the art

https://arxiv.org/pdf/2103.14030.pdf

There have a few variants:

• Swin-T: C = 96, layer numbers = {2, 2, 6, 2}
• Swin-S: C = 96, layer numbers ={2, 2, 18, 2}
• Swin-B: C = 128, layer numbers ={2, 2, 18, 2}
• Swin-L: C = 192, layer numbers ={2, 2, 18, 2}