C1_W4_E8 - error with results, althoough equations are true

[oferbar]

In the exercise “8 - linear_activation_backward” I believe I got it right. i watched the videos over and over and read some of the related topics. and still the output is wrong. I truly believe there might be a bug in it. All exercises previously turned out successful results.
A solution like so would yield wrong results:

{moderator edit - solution code removed}

yields wrong outputs:

With sigmoid: dA_prev = [[-0.04591835 -0.00062194]
 [-0.0394537  -0.00053438]
 [ 0.02393479  0.00032418]]
With sigmoid: dW = [[-0.04587658 -0.03916771  0.01054726]]
With sigmoid: db = [[0.02199546]]
With relu: dA_prev = [[-0.18375266  0.        ]
 [-0.1578829   0.        ]
 [ 0.09578046  0.        ]]
With relu: dW = [[-0.18551486 -0.15574832  0.04367201]]
With relu: db = [[0.08684355]]
Error: Wrong output with sigmoid activation for variable 0.
Error: Wrong output with sigmoid activation for variable 1.
Error: Wrong output with sigmoid activation for variable 2.
Error: Wrong output with relu activation for variable 0.
Error: Wrong output with relu activation for variable 1.
Error: Wrong output with relu activation for variable 2.
 4  Tests passed
 2  Tests failed

Please help!

[vxidh]

I think you’ve misread as to what sigmoid_backward and relu_backward do.
Right above exercise 8, it is written that they compute:-
dZ= dA* g’(Z)
You don’t have to multiply the function with dA again, as it is already done by the function
Cheers

[oferbar]

Thanks!