Error in computing cost in Week 2 Exercise

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

{moderator edit - solution code removed}

w = np.array([[1.], [2]])
b = 1.5
X = np.array([[1., -2., -1.], [3., 0.5, -3.2]])
Y = np.array([[1, 1, 0]])
grads, cost = propagate(w, b, X, Y)

assert type(grads[“dw”]) == np.ndarray
assert grads[“dw”].shape == (2, 1)
assert type(grads[“db”]) == np.float64

print ("dw = " + str(grads[“dw”]))
print ("db = " + str(grads[“db”]))
print ("cost = " + str(cost))

propagate_test(propagate)

I am getting the below error for cost. I am not understanding what is wrong with the cost.

dw = [[ 0.25071532] [-0.06604096]] db = -0.12500404500439652 cost = [[6.78158907e-05 1.58025661e-01 1.96757857e+00] [6.78158907e-05 1.58025661e-01 1.96757857e+00] [2.83340115e+00 3.24692328e-01 9.11899793e-04]] ---------------------------------------------------------------------------AssertionError Traceback (most recent call last) in 14 print (“cost = “+ str(cost)) 15—> 16propagate_test(propagate)~/work/release/W2A2/public_tests.py in propagate_test(target) 41assert np.allclose(grads[‘dw’], expected_dw),f"Wrong values for grads[‘dw’]. {grads[‘dw’]} != {expected_dw}” 42assert np.allclose(grads[‘db’], expected_db),f"Wrong values for grads[‘db’]. {grads[‘db’]} != {expected_db}”—> 43assert np.allclose(cost, expected_cost),f"Wrong values for cost. {cost} != {expected_cost}" 44 print(’\033[92mAll tests passed!’) 45AssertionError: Wrong values for cost. [[3.75577540e-04 5.08619180e-05 4.66946507e-01 8.38515932e-05] [3.75577540e-04 5.08619180e-05 4.66946507e-01 8.38515932e-05] [1.62537558e+00 2.12505086e+00 4.19465073e-02 2.00008385e+00] [1.62537558e+00 2.12505086e+00 4.19465073e-02 2.00008385e+00]] != 2.0424567983978403

2

You can see that the problem is that your cost value ends up being a 3 x 3 matrix in the first case and a 4 x 4 matrix in the second case. So how could that happen? Note that in the first test case, both Y and A are 1 x 3 vectors. So Y^T is 3 x 1. If you dot 3 x 1 with 1 x 3, you get a 3 x 3 matrix, right? I don’t think that is what you want for the cost.

Here’s a previous thread that works through some examples that are relevant to the problem here.

3

Thanks, Paul for your help. It is resolved.