DLS 4, Week 3, Exercise 2 - wrong grading

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi all,

The code is running good and there are no errors. The prediction results look excellent as well.

However, for some weird reason the grader give 66/100 - just enough to pass it.

Is there a problem with the grader?

Following is the message it give:
*Code Cell UNQ_C3: Function ‘unet_model’ is incorrect. Check implementation. *
If you see many functions being marked as incorrect, try to trace back your steps & identify if there is an incorrect function that is being used in other steps.
This dependency may be the cause of the errors.

Regards,
Sam

2

Never mind, figured out the issues :slight_smile:

3

Could you leave a clue about what the problem was?

4

TMosh - the issue is resolved.

Thanks for following up though.

5

It would help the community if you added some information on how you fixed the issue.
This is particularly important since you raised a question about whether the grader works correctly.

6

Could you help on the issue please?

7

I had the same message. I found out that in my case the problem was because I used 23 directly instead of n_classes for conv10.

2 Likes
8

Correct - if you manually input numbers instead of “n”, you will get wrong grading error.