def __init__(
self,
log_interval: Union[int, float] = -1,
log_val_interval: Union[int, float] = None,
learning_rate: Union[float, List[float]] = 1e-3,
log_gradient_flow: bool = False,
loss: Metric = SMAPE(),
logging_metrics: nn.ModuleList = nn.ModuleList([]),
reduce_on_plateau_patience: int = 1000,
weight_decay: float = 0.0,
monotone_constaints: Dict[str, int] = {},
output_transformer: Callable = None,
optimizer="ranger",
):
"""
BaseModel for timeseries forecasting from which to inherit from
Args:
log_interval (Union[int, float], optional): Batches after which predictions are logged. If < 1.0, will log
multiple entries per batch. Defaults to -1.
log_val_interval (Union[int, float], optional): batches after which predictions for validation are
logged. Defaults to None/log_interval.
learning_rate (float, optional): Learning rate. Defaults to 1e-3.
log_gradient_flow (bool): If to log gradient flow, this takes time and should be only done to diagnose
training failures. Defaults to False.
loss (Metric, optional): metric to optimize. Defaults to SMAPE().
logging_metrics (nn.ModuleList[MultiHorizonMetric]): list of metrics that are logged during training.
Defaults to [].
reduce_on_plateau_patience (int): patience after which learning rate is reduced by a factor of 10. Defaults
to 1000
weight_decay (float): weight decay. Defaults to 0.0.
monotone_constaints (Dict[str, int]): dictionary of monotonicity constraints for continuous decoder
variables mapping
position (e.g. ``"0"`` for first position) to constraint (``-1`` for negative and ``+1`` for positive,
larger numbers add more weight to the constraint vs. the loss but are usually not necessary).
This constraint significantly slows down training. Defaults to {}.
output_transformer (Callable): transformer that takes network output and transforms it to prediction space.
Defaults to None which is equivalent to ``lambda out: out["prediction"]``.
optimizer (str): optimizer
"""
super().__init__()
# update hparams
frame = inspect.currentframe()
init_args = get_init_args(frame)
self.save_hyperparameters({
name: val
for name, val in init_args.items() if name not in self.hparams
})
# update log interval if not defined
if self.hparams.log_val_interval is None:
self.hparams.log_val_interval = self.hparams.log_interval
if not hasattr(self, "loss"):
self.loss = loss
if not hasattr(self, "logging_metrics"):
self.logging_metrics = nn.ModuleList([l for l in logging_metrics])
if not hasattr(self, "output_transformer"):
self.output_transformer = output_transformer
def get_init_args_wrapper(self):
frame = inspect.currentframe().f_back
self.result = get_init_args(frame)
