avalanche.evaluation.metrics.RMSE

class avalanche.evaluation.metrics.RMSE

RMSE metric. This is a standalone metric.

The update method computes the RMSE incrementally by keeping a running average of the <prediction, target> pairs of Tensors provided over time.

The “prediction” and “target” tensors may contain plain labels or one-hot/logit vectors.

Each time result is called, this metric emits the average RMSE across all predictions made since the last reset.

The reset method will bring the metric to its initial state. By default this metric in its initial state will return an RMSE value of 0.

__init__()

Creates an instance of the standalone RMSE metric.

By default this metric in its initial state will return an RMSE value of 0. The metric can be updated by using the update method while the running RMSE can be retrieved using the result method.

Methods

__init__()	Creates an instance of the standalone RMSE metric.
reset()	Resets the metric.
result()	Retrieves the running RMSE.
update(predicted_y, true_y)	Update the running RMSE given the true and predicted labels.