Basic Transformer

class flood_forecast.transformer_xl.transformer_basic.SimpleTransformer(number_time_series: int, seq_length: int = 48, output_seq_len: Optional[int] = None, d_model: int = 128, n_heads: int = 8, dropout=0.1, forward_dim=2048, sigmoid=False)

__init__(number_time_series: int, seq_length: int = 48, output_seq_len: Optional[int] = None, d_model: int = 128, n_heads: int = 8, dropout=0.1, forward_dim=2048, sigmoid=False)

Full transformer model

forward(x: torch.Tensor, t: torch.Tensor, tgt_mask=None, src_mask=None)

Defines 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.

basic_feature(x: torch.Tensor)

encode_sequence(x, src_mask=None)

decode_seq(mem, t, tgt_mask=None, view_number=None) → torch.Tensor

training: bool

class flood_forecast.transformer_xl.transformer_basic.CustomTransformerDecoder(seq_length: int, output_seq_length: int, n_time_series: int, d_model=128, output_dim=1, n_layers_encoder=6, forward_dim=2048, dropout=0.1, use_mask=False, meta_data=None, final_act=None, n_heads=8)

__init__(seq_length: int, output_seq_length: int, n_time_series: int, d_model=128, output_dim=1, n_layers_encoder=6, forward_dim=2048, dropout=0.1, use_mask=False, meta_data=None, final_act=None, n_heads=8)

Uses a number of encoder layers with simple linear decoder layer.

make_embedding(x: torch.Tensor)

forward(x: torch.Tensor, meta_data=None) → torch.Tensor

Performs forward pass on tensor of (batch_size, sequence_length, n_time_series) Return tensor of dim (batch_size, output_seq_length)

training: bool

class flood_forecast.transformer_xl.transformer_basic.SimplePositionalEncoding(d_model, dropout=0.1, max_len=5000)

__init__(d_model, dropout=0.1, max_len=5000)

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

forward(x: torch.Tensor) → torch.Tensor

Creates a basic positional encoding

training: bool

flood_forecast.transformer_xl.transformer_basic.greedy_decode(model, src: torch.Tensor, max_len: int, real_target: torch.Tensor, unsqueeze_dim=1, output_len=1, device='cpu', multi_targets=1, probabilistic=False, scaler=None)

Mechanism to sequentially decode the model :src The Historical time series values :real_target The real values (they should be masked), however if you want can include known real values. :returns torch.Tensor