dsipts.models.crossformer package¶
Submodules¶
dsipts.models.crossformer.attn module¶
- class dsipts.models.crossformer.attn.AttentionLayer(d_model, n_heads, d_keys=None, d_values=None, mix=True, dropout=0.1)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(queries, keys, values)¶
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.attn.FullAttention(scale=None, attention_dropout=0.1)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(queries, keys, values)¶
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.attn.TwoStageAttentionLayer(seg_num, factor, d_model, n_heads, d_ff=None, dropout=0.1)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)¶
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.
dsipts.models.crossformer.cross_decoder module¶
- class dsipts.models.crossformer.cross_decoder.Decoder(seg_len, d_layers, d_model, n_heads, d_ff, dropout, router=False, out_seg_num=10, factor=10)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x, cross)¶
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_decoder.DecoderLayer(seg_len, d_model, n_heads, d_ff=None, dropout=0.1, out_seg_num=10, factor=10)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x, cross)¶
x: the output of last decoder layer cross: the output of the corresponding encoder layer
dsipts.models.crossformer.cross_embed module¶
- class dsipts.models.crossformer.cross_embed.DSW_embedding(seg_len, d_model)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)¶
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.
dsipts.models.crossformer.cross_encoder module¶
- 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)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)¶
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.SegMerging(d_model, win_size, norm_layer=<class 'torch.nn.modules.normalization.LayerNorm'>)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)¶
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)¶
Bases:
Module
Initialize internal Module state, shared by both nn.Module and ScriptModule.
- forward(x)¶
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.