W1_Assign3_ Your results may likely differ because Keras' results are not completely predictable

Hello! I hope you are doing well.
I got this point that my results may differ but I got no error and scored 66%. I am curious what mistake(s) I am making. Can you please assist?
Grader feedback is:

Code Cell UNQ_C1: Function 'djmodel' is correct.
Code Cell UNQ_C2: Function 'music_inference_model' is correct.
Code Cell UNQ_C3: Unexpected error (ValueError('operands could not be broadcast together with shapes (13,83) (13,90) ')) occurred during function check. We expected function `predict_and_sample` to return Test 3 failed. Please check that this function is defined properly. 
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.

Hey @saifkhanengr,
Can you please confirm if you are passing all the test-cases mentioned in the notebook? If yes, if you are not able to find the error in your implementation, please DM your notebook as an attachment to me.

It happens often that there is an error in the implementations of the previous functions, but the grader catches them in the following functions, so it may be possible for the error to be in the predict_and_sample function, but it is also possible for the error to be in the previous functions.

As per the grader’s output, my most likely bet would be to check for the shapes of the variables, since the operands seem to have different shapes.


Hello Elemento! Thanks for your reply.
I just figured out my mistake and corrected it. It was some Python-related mistake. But I highly appreciate your time.

1 Like