Course 1, Week 2, Exercise 5

[Michael_Lappert]

Hey there
I found already some other topics about this Exercise, but none seems to fit my problem: In my opinion i have implemented the right functions. But i do get error messages that the results do not match. Could you please point me out, what i oversee? (I post this as well because i have read there were some issues with the test)

---

AssertionError Traceback (most recent call last)
in
14 print ("cost = " + str(cost))
15
—> 16 propagate_test(propagate)

~/work/release/W2A2/public_tests.py in propagate_test(target)
39 assert type(grads[‘dw’]) == np.ndarray, f"Wrong type for grads[‘dw’]. {type(grads[‘dw’])} != np.ndarray"
40 assert grads[‘dw’].shape == w.shape, f"Wrong shape for grads[‘dw’]. {grads[‘dw’].shape} != {w.shape}"
—> 41 assert np.allclose(grads[‘dw’], expected_dw), f"Wrong values for grads[‘dw’]. {grads[‘dw’]} != {expected_dw}"
42 assert np.allclose(grads[‘db’], expected_db), f"Wrong values for grads[‘db’]. {grads[‘db’]} != {expected_db}"
43 assert np.allclose(cost, expected_cost), f"Wrong values for cost. {cost} != {expected_cost}"

AssertionError: Wrong values for grads[‘dw’]. [[-0.00942637]
[ 0.22120096]
[-0.89922014]] != [[-0.03909333]
[ 0.12501464]
[-0.99960809]]

Many thanks in advance for any help!

Best Michael

[Michael_Lappert]

It was a problem with the calculation of the activation matrix. I never checked this one before and just found out, that i had some issue there. Maybe this helps others as well…

[Rizama_Victor]

I experienced a similar issue as @Michael_Lappert but the error I received was “Wrong values for cost” function. I have tried computing the loss using different ways over the past couple of days now but unfortunately, I still keep getting this same error. Please can any one help

[Rashmi]

Hello Rizama,

Are you sure that you are applying the correct formula into the equations?

Forward Propagation:

You get X
You compute  𝐴=𝜎(𝑤𝑇𝑋+𝑏)=(𝑎(1),𝑎(2),...,𝑎(𝑚−1),𝑎(𝑚)) 
You calculate the cost function:  𝐽=−1𝑚∑𝑚𝑖=1(𝑦(𝑖)log(𝑎(𝑖))+(1−𝑦(𝑖))log(1−𝑎(𝑖))) 
Here are the two formulas you will be using:

∂𝐽∂𝑤=1𝑚𝑋(𝐴−𝑌)𝑇(7)
∂𝐽∂𝑏=1𝑚∑𝑖=1𝑚(𝑎(𝑖)−𝑦(𝑖))(8)

[Rizama_Victor]

Yes, that was the issue. The cost function formula was correct just that I transposed the wrong matrices. I already fixed it. Thanks for the assistance

[Rashmi]

Good to know that Rizama!

Keep learning!

[Junta442]

Hi there @Rashmi could you assist I’m getting an error
C1 W2 Logistic Regression Excercise 4
AssertionError Traceback (most recent call last)
in
2 w, b = initialize_with_zeros(dim)
3
----> 4 assert type(b) == float
5 print ("w = " + str(w))
6 print ("b = " + str(b))

AssertionError:

[paulinpaloalto]

If this is your first encounter with the “assert” statement in python, it is checking for a condition that is supposed to evaluate to True (boolean) and it fails or “throws” if it is not true. So what is the condition that is failing in your case? It is shown by the statement:

@Junta442

type(b) == float

So your b value is supposed to be a python float, but it isn’t. So how did that happen? You probably assigned b with the value 0, but that is an integer value in python. Note that 0 and 0. are not the same thing in python. That decimal point makes the value a floating point number.