self-adj-dice icon indicating copy to clipboard operation
self-adj-dice copied to clipboard

Implementation of Self-adjusting Dice Loss from "Dice Loss for Data-imbalanced NLP Tasks" paper

Results 2 self-adj-dice issues
Sort by recently updated
recently updated
newest added

Hello, Yours Dice_loss is for multiple classifications. If don’t want loss, just ask Dice_coff. Is the code as follows? ` def calculate_loss(logits: np.ndarray, targets: np.ndarray, alpha: float = 1.0, gamma:...

Hi there ! First, thanks for the code :) I am gonna try Dice Loss for a NLP Project I am contributing to and I was wondering if you felt...