mse

behavenet.fitting.losses.mse(y_pred, y_true, masks=None)[source]

Compute mean square error (MSE) loss with masks.

Parameters:

  • y_pred (torch.Tensor) – predicted data

  • y_true (torch.Tensor) – true data

  • masks (torch.Tensor, optional) – binary mask that is the same size as y_pred and y_true; by placing 0 entries in the mask, the corresponding dimensions will not contribute to the loss term, and will therefore not contribute to parameter updates

Returns:

mean square error computed across all dimensions

Return type:

torch.Tensor