PoissonLoss

class pytorch_forecasting.metrics.PoissonLoss(reduction: str = 'mean', **kwargs)

Bases: pytorch_forecasting.metrics.MultiHorizonMetric

Poisson loss for count data

Initialize metric

Parameters

• name (str) – metric name. Defaults to class name.

• quantiles (List[float], optional) – quantiles for probability range. Defaults to None.

• reduction (str, optional) – Reduction, “none”, “mean” or “sqrt-mean”. Defaults to “mean”.

Methods

loss(y_pred, target)	Calculate loss without reduction.
to_prediction(out)	Convert network prediction into a point prediction.
to_quantiles(out[, quantiles])	Convert network prediction into a quantile prediction.

loss(y_pred: Dict[str, torch.Tensor], target: torch.Tensor) → torch.Tensor

Calculate loss without reduction. Override in derived classes

Parameters

• y_pred – network output

• y_actual – actual values

Returns

loss/metric as a single number for backpropagation

Return type

torch.Tensor

to_prediction(out: Dict[str, torch.Tensor])

Convert network prediction into a point prediction.

Parameters

y_pred – prediction output of network

Returns

point prediction

Return type

torch.Tensor

to_quantiles(out: Dict[str, torch.Tensor], quantiles=None)

Convert network prediction into a quantile prediction.

Parameters

y_pred – prediction output of network

Returns

prediction quantiles

Return type

torch.Tensor

NormalDistributionLoss QuantileLoss