Losses: Cutoff MSE¶
-
class
losses.
CutoffMSE
(cutoffValue=1)¶ Description:
Cutoff MSE loss has two steps:
- Filtering:
- Filter the noisy labels out by comparing their noise variances to a threshold. Remove the label if its noise variance is bigger than a threshold, otherwise, use it to compute the loss.
- MSE loss:
- Compute the mse loss using the filtered labels.
- Args:
threshold: An upper bound noise variance threshold to filter out the noisy labels.
-
forward
(y_pred, y, lbl_var)¶ - Description:
- Compute the forward pass.