SingleShotTransformer#

class SingleShotTransformer(encoding_length, decoding_length, target_names, nontarget_names, d_model, n_heads, n_layers, dim_feedforward=None, dropout_rate=0.0, lr=0.001, optimizer=<class 'torch.optim.adam.Adam'>, optimizer_options=None, loss_fn=None, metrics=None, head=None)[source]#

Bases: ForecastingModule

Methods

`configure_optimizers`
`decode`
`encode`
`generate_square_subsequent_mask`	Generate a square mask for the sequence.
`make_chunk_specs`

Attributes

Parameters:: optimizer (Optimizer) –

generate_square_subsequent_mask(sz)[source]#: Generate a square mask for the sequence. The masked positions are filled with float(‘-inf’). Unmasked positions are filled with float(0.0).