r""" Swin Transformer A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` - https://arx

A basic Swin Transformer layer for one stage. Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input

Obtained from: github.com:rwightman/pytorch-image-models Drop paths (Stochastic Depth) per sample (when applied in main path of residual b

r""" Image to Patch Embedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

Patch Merging Layer Args: dim (int): Number of input channels. norm_layer (nn.Module, optional): Normalization layer. Default

r""" Swin Transformer Block. Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input resulotion.

r""" Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window.