MIR.models.Swin_TransformerΒΆ

Swin Transformer backbone for 3D medical image registration.

Functions

window_partition(x, window_size)

Partition a channel-last 3D feature map into non-overlapping windows.

window_reverse(windows, window_size, H, W, L)

Merge windows produced by window_partition() back into a 3D feature map.

Classes

BasicLayer(*args, **kwargs)

A basic Swin Transformer layer for one stage.

Mlp(*args, **kwargs)

Feed-forward MLP block used inside transformer blocks.

PatchEmbed(*args, **kwargs)

Image to Patch Embedding using a strided 3D convolution.

PatchMerging(*args, **kwargs)

Patch Merging Layer.

SinPositionalEncoding3D(*args, **kwargs)

Fixed 3D sinusoidal positional encoding.

SinusoidalPositionEmbedding(*args, **kwargs)

Fixed sinusoidal (1D, absolute) position embedding for a token sequence.

SwinTransformer(*args, **kwargs)

3D Swin Transformer encoder.

SwinTransformerBlock(*args, **kwargs)

Swin Transformer Block.

WindowAttention(*args, **kwargs)

Window based multi-head self attention (W-MSA) module with relative position bias.