Simple Multi Attention Head Model¶
-
class
flood_forecast.transformer_xl.multi_head_base.
MultiAttnHeadSimple
(number_time_series: int, seq_len=10, output_seq_len=None, d_model=128, num_heads=8, forecast_length=None, dropout=0.1, final_layer=False)[source]¶ A simple multi-head attention model inspired by Vaswani et al.
-
__init__
(number_time_series: int, seq_len=10, output_seq_len=None, d_model=128, num_heads=8, forecast_length=None, dropout=0.1, final_layer=False)[source]¶ Initializes internal Module state, shared by both nn.Module and ScriptModule.
-
forward
(x: torch.Tensor, mask=None) → torch.Tensor[source]¶ - Param
x torch.Tensor: of shape (B, L, M)
Where B is the batch size, L is the sequence length and M is the number of time :return: a tensor of dimension (B, forecast_length)
-
training
: bool¶
-