Shift Window-based multi-head self-attention module.

Shift Window-based multi-head self-attention module.

Simple residual unit.

Simple residual unit.

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

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

r"""Entropy bottleneck layer, introduced by J. Ballé, D. Minnen, S. Singh, S. J. Hwang, N. Johnston, in `"Variational image compression with a sca

r"""Entropy bottleneck layer, introduced by J. Ballé, D. Minnen, S. Singh, S. J. Hwang, N. Johnston, in `"Variational image compression with a sca

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

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

Base class for constructing an auto-encoder with at least one entropy bottleneck module. Args: entropy_bottleneck_channels (int): Num

Base class for constructing an auto-encoder with at least one entropy bottleneck module. Args: entropy_bottleneck_channels (int): Num