Hello Yosilia,
Kindly remove the codes from your post. It is against community guidelines. You can always share a screenshot of your error or your output in comparison to the expected output.
-
Have you noticed that DO NOT EDIT?? …there is no import statement for UNQ_C5 cell. You have edited the grader cell, which will lead you to grader failure when you submit your assignment.
-
If you have read these instructions before the cell
We’ve explained the single class case for simplicity, but the multi-class generalization is exactly the same as that of the dice coefficient.
- Since you’ve already implemented the multi-class dice coefficient, we’ll have you jump directly to the multi-class soft dice loss.
you will understand you need to define the dice_loss as per the K.mean instructions, but before that recall dice_numerator and dice_denominator where you would use K.sum for your predictive and true labels with axis and the epsilon factor.
Your codes are incorrect for UNQ_C5 and if you have followed the same code pattern for C4, then you need to correct them too.
Regards
DP