Kaggle-Carvana-Image-Masking-Challenge
Kaggle-Carvana-Image-Masking-Challenge copied to clipboard
problem about dice_coeff
Thanks for sharing your work, but I have a problem in the loss function. In dice_coeff, y_true is a label, but y_pred is a probility, what does dice_coeff mean? I know when y_pred is also a label, dice_coeff is a proper evaluation in this task.