Course 5, Week4 - Wrong values in Encoder unit-test

Course Q&A Deep Learning Specialization Sequence Models
1

Hi,
I couldn’t pass the unit test after implementing UNQ_C5 (Encoder). I passed all unit test for previous exercises. Generated values are different.
How could I debug the implementation without revealing the code?
I will be grateful for any tips. I didn’t use the sum function in the EncoderLayer.
Here is printed actual values
----Actual values:
[[[-0.41014948 0.12101075 -1.229354 1.5184926 ]
[ 0.37789708 0.33369446 -1.6772832 0.9656917 ]
[ 0.47270587 -1.6204187 0.07778789 1.069925 ]]

[[-0.3631447 0.29704505 -1.3413051 1.4074047 ]
[-0.09853393 -0.16293095 -1.2709734 1.5324383 ]
[ 0.26958477 -1.6148064 0.21713856 1.1280832 ]]]

— Expected (from the test)
[[[-0.40172306, 0.11519244, -1.2322885, 1.5188192 ],
[ 0.4017268, 0.33922842, -1.6836855, 0.9427304 ],
[ 0.4685002, -1.6252842, 0.09368491, 1.063099 ]],
[[-0.3489219, 0.31335592, -1.3568854, 1.3924513 ],
[-0.08761203, -0.1680029, -1.2742313, 1.5298463 ],
[ 0.2627198, -1.6140151, 0.2212624 , 1.130033 ]]]

2

Usually you can get some tips by searching the Forum for the function name you’re working on.