spacetimeformer.lstnet_model package
- class spacetimeformer.lstnet_model.LSTNet.LSTNet(window: int, m: int, hidRNN: int, hidCNN: int, hidSkip: int, CNN_kernel: int, skip: int, highway_window: int, dropout: float, output_fun: str)[source]
Bases:
torch.nn.modules.module.Module
- forward(y_c)[source]
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.
- training: bool
- class spacetimeformer.lstnet_model.lstnet_model.LSTNet_Forecaster(context_points: int, d_y: int, hidRNN: int = 100, hidCNN: int = 100, hidSkip: int = 5, CNN_kernel: int = 7, skip: int = 24, dropout_p: float = 0.2, output_fun: Optional[str] = None, learning_rate: float = 0.001, l2_coeff: float = 0, loss: str = 'mse', linear_window: int = 0)[source]
Bases:
spacetimeformer.forecaster.Forecaster
- allow_zero_length_dataloader_with_multiple_devices: bool
- property eval_step_forward_kwargs
- precision: int
- prepare_data_per_node: bool
- property train_step_forward_kwargs
- training: bool
- use_amp: bool