dsipts.models.crossformer.cross_encoder module

class dsipts.models.crossformer.cross_encoder.SegMerging(d_model, win_size, norm_layer=nn.LayerNorm)[source]

Bases: Module

Segment Merging Layer. The adjacent `win_size’ segments in each dimension will be merged into one segment to get representation of a coarser scale we set win_size = 2 in our paper

Initialize internal Module state, shared by both nn.Module and ScriptModule.

__init__(d_model, win_size, norm_layer=nn.LayerNorm)[source]

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]

x: B, ts_d, L, d_model

class dsipts.models.crossformer.cross_encoder.scale_block(win_size, d_model, n_heads, d_ff, depth, dropout, seg_num=10, factor=10)[source]

Bases: Module

We can use one segment merging layer followed by multiple TSA layers in each scale the parameter `depth’ determines the number of TSA layers used in each scale We set depth = 1 in the paper

Initialize internal Module state, shared by both nn.Module and ScriptModule.

__init__(win_size, d_model, n_heads, d_ff, depth, dropout, seg_num=10, factor=10)[source]

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class dsipts.models.crossformer.cross_encoder.Encoder(e_blocks, win_size, d_model, n_heads, d_ff, block_depth, dropout, in_seg_num=10, factor=10)[source]

Bases: Module

The Encoder of Crossformer.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

__init__(e_blocks, win_size, d_model, n_heads, d_ff, block_depth, dropout, in_seg_num=10, factor=10)[source]

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.