root_mean_squared_error#

bayesflow.metrics.functional.root_mean_squared_error(x1: Tensor, x2: Tensor, normalize: bool = False, **kwargs) → Tensor[source]#

Computes the (normalized) root mean squared error between samples x1 and x2.

Parameters:

  • x1 – Tensor of shape (n, …)

  • x2 – Tensor of shape (n, …)

  • normalize – Normalize the RMSE?

  • kwargs – Currently ignored

Returns:

Tensor of shape (n,) The RMSE between x1 and x2 over all remaining dimensions.