The Multi-head Self-Attention (MSA) Layer

The Two Stage Attention (TSA) Layer input/output shape: [batch_size, Data_dim(D), Seg_num(L), d_model]

We can use one segment merging layer followed by multiple TSA layers in each scale the parameter `depth' determines the number of TSA layers

The decoder of Crossformer, making the final prediction by adding up predictions at each scale

The decoder layer of Crossformer, each layer will make a prediction at its scale

The Encoder of Crossformer.

The Attention operation

Segment Merging Layer. The adjacent `win_size' segments in each dimension will be merged into one segment to get representation of a coar