sub_modules

Implementation of nn.Modules for TimeXer model.

Classes

AttentionLayer(attention, d_model, n_heads)	Attention layer that combines query, key, and value projections with an attention mechanism.
DataEmbedding_inverted(c_in, d_model[, ...])	Data embedding module for time series data.
EnEmbedding(n_vars, d_model, patch_len, dropout)	Encoder embedding module for time series data.
Encoder(layers[, norm_layer, projection])	Encoder module for the TimeXer model.
EncoderLayer(self_attention, ...[, d_ff, ...])	Encoder layer for the TimeXer model.
FlattenHead(n_vars, nf, target_window[, ...])	Flatten head for the output of the model.
FullAttention([mask_flag, factor, scale, ...])	Full attention mechanism with optional masking and dropout.
PositionalEmbedding(d_model[, max_len])	Positional embedding module for time series data.
TriangularCausalMask(B, L[, device])	Triangular causal mask for attention mechanism.