TabularForecaster¶

class flash.tabular.forecasting.model.TabularForecaster(parameters, backbone, backbone_kwargs=None, loss_fn=None, optimizer='Adam', lr_scheduler=None, metrics=None, learning_rate=None)[source]¶

classmethod available_finetuning_strategies(cls)¶

Returns a list containing the keys of the available Finetuning Strategies.

Return type: List[str]

classmethod available_lr_schedulers(cls)¶

Returns a list containing the keys of the available LR schedulers.

Return type: List[str]

classmethod available_optimizers(cls)¶

Returns a list containing the keys of the available Optimizers.

Return type: List[str]

classmethod available_outputs(cls)¶

Returns the list of available outputs (that can be used during prediction or serving) for this Task.

Examples

..testsetup:

>>> from flash import Task

>>> print(Task.available_outputs())
['preds', 'raw']

Return type: List[str]

property pytorch_forecasting_model: pytorch_lightning.LightningModule¶

This property provides access to the LightningModule object that is wrapped by Flash for backbones provided by PyTorch Forecasting.

This can be used with convert_predictions() to access the visualization features built in to PyTorch Forecasting.

Return type: LightningModule