Week 3, module 2 - Planar data classification with one hidden layer, 4.4 - Compute the Cost

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

Hi, I have a error in this part of the code. All above codes are validated.

{Moderator Edit: Solution Code Removed}

the result is cost = 0.6926858869721941
Expected output
cost = 0.6930587610394646

I dont know what is wrong, anybody can help?
Then I have a error:

AssertionError Traceback (most recent call last)
in
3 print("cost = " + str(compute_cost(A2, t_Y)))
4
----> 5 compute_cost_test(compute_cost)

~/work/release/W3A1/public_tests.py in compute_cost_test(target)
131
132 assert type(output_1) == float, “Wrong type. Float expected”
→ 133 assert np.isclose(output_1, expected_output_1), f"Wrong value. Expected: {expected_output_1} got: {output_1}"
134
135 assert type(output_2) == float, “Wrong type. Float expected”

AssertionError: Wrong value. Expected: 0.5447066599017815 got: 1.0493608309109266

2

The order of variables also matters. Check this for further guidance.

Also, you are computing one term only. This is the full formula:

J = - \frac{1}{m} \sum\limits_{i = 1}^{m} \large{(} \small y^{(i)}\log\left(a^{[2] (i)}\right) + (1-y^{(i)})\log\left(1- a^{[2] (i)}\right) \large{)}

3

Thanks a lot, the partially formula was the problem.