Course 5 Week 4 Programming Assignment Grading Error

Course Q&A Deep Learning Specialization Sequence Models
1

I think I correctly implemented “Transformer” (it is quite straight forward) but got a grading error as follows:

Code Cell UNQ_C1: Function ‘get_angles’ is correct.
Code Cell UNQ_C2: Function ‘positional_encoding’ is correct.
Code Cell UNQ_C3: Function ‘scaled_dot_product_attention’ is correct.
Code Cell UNQ_C4: Function ‘EncoderLayer’ is correct.
Code Cell UNQ_C5: Function ‘Encoder’ is correct.
Code Cell UNQ_C6: Function ‘DecoderLayer’ is correct.
Code Cell UNQ_C7: Function ‘Decoder’ is correct.
Code Cell UNQ_C8: Unexpected error (InvalidArgumentError()) occurred during function check. We expected function Transformer to return type <class ‘tuple’>. 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.

3

What helped me was to Restart the Kernel and clear the output, and afterwards run all cells again, then submit the assignment again.

=> 100/100!

4

Hi, Tyyim!

You should notice that the the expected function must return as tuple. Check, whether you are implementing it correctly.