Week3 assignment exercise8 'wrong values W1 error'

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

I have an error that says ‘wrong values W1 error’, but the result are totally same with the expected output.

Oviously, I didn’t use -= operand in previous function definition. I used ‘W1 = W1 - (learning_rate * dW1)’

What is the problem?

Cost after iteration 0: 0.692739
Cost after iteration 1000: 0.000218
Cost after iteration 2000: 0.000107
Cost after iteration 3000: 0.000071
Cost after iteration 4000: 0.000053
Cost after iteration 5000: 0.000042
Cost after iteration 6000: 0.000035
Cost after iteration 7000: 0.000030
Cost after iteration 8000: 0.000026
Cost after iteration 9000: 0.000023
W1 = [[-0.65848169 1.21866811]
[-0.76204273 1.39377573]
[ 0.5792005 -1.10397703]
[ 0.76773391 -1.41477129]]
b1 = [[ 0.287592 ]
[ 0.3511264 ]
[-0.2431246 ]
[-0.35772805]]
W2 = [[-2.45566237 -3.27042274 2.00784958 3.36773273]]
b2 = [[0.20459656]]

AssertionError Traceback (most recent call last)
in
7 print("b2 = " + str(parameters[“b2”]))
8
----> 9 nn_model_test(nn_model)

~/work/release/W3A1/public_tests.py in nn_model_test(target)
273 assert output[“b2”].shape == expected_output[“b2”].shape, f"Wrong shape for b2."
274
→ 275 assert np.allclose(output[“W1”], expected_output[“W1”]), “Wrong values for W1”
276 assert np.allclose(output[“b1”], expected_output[“b1”]), “Wrong values for b1”
277 assert np.allclose(output[“W2”], expected_output[“W2”]), “Wrong values for W2”

AssertionError: Wrong values for W1

Expected output

Cost after iteration 0: 0.692739
Cost after iteration 1000: 0.000218
Cost after iteration 2000: 0.000107
…
Cost after iteration 8000: 0.000026
Cost after iteration 9000: 0.000023
W1 = [[-0.65848169 1.21866811]
[-0.76204273 1.39377573]
[ 0.5792005 -1.10397703]
[ 0.76773391 -1.41477129]]
b1 = [[ 0.287592 ]
[ 0.3511264 ]
[-0.2431246 ]
[-0.35772805]]
W2 = [[-2.45566237 -3.27042274 2.00784958 3.36773273]]
b2 = [[0.20459656]]

2

that exactly my problem

3

That’s great that you have not used the “inplace” operator in the gradient ascent. You’re right, it is important, but not so obvious to those new to Python! :nerd_face:

First up, please see this thread initiated just before yours.