Week 3 Exercise 3, Initialize_parameters - wrong W1

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

Get wrong W1, this is my code…
Can anyone help?

4.2 - Initialize the model’s parameters

Exercise 3 - initialize_parameters

2

The code seems fine, but you are not allowed to post this publicly!

What are you getting as the output after the test code?

3

W1 = [[0.00435995 0.00025926]
[0.00549662 0.00435322]
[0.00420368 0.00330335]
[0.00204649 0.00619271]]
b1 = [[0.]
[0.]
[0.]
[0.]]
W2 = [[0.00299655 0.00266827 0.00621134 0.00529142]]
b2 = [[0.]]

AssertionError Traceback (most recent call last)
in
8 print("b2 = " + str(parameters[“b2”]))
9
—> 10 initialize_parameters_test(initialize_parameters)

~/work/release/W3A1/public_tests.py in initialize_parameters_test(target)
57 assert parameters[“b2”].shape == expected_output[“b2”].shape, f"Wrong shape for b2."
58
—> 59 assert np.allclose(parameters[“W1”], expected_output[“W1”]), “Wrong values for W1”
60 assert np.allclose(parameters[“b1”], expected_output[“b1”]), “Wrong values for b1”
61 assert np.allclose(parameters[“W2”], expected_output[“W2”]), “Wrong values for W2”

AssertionError: Wrong values for W1

Expected output

W1 = [[-0.00416758 -0.00056267]
[-0.02136196 0.01640271]
[-0.01793436 -0.00841747]
[ 0.00502881 -0.01245288]]
b1 = [[0.]
[0.]
[0.]
[0.]]
W2 = [[-0.01057952 -0.00909008 0.00551454 0.02292208]]
b2 = [[0.]]
All tests passed!

4

Hi @yuvalbz ,

Please check that you are using np.random.randn() to generate W1, and W2

5

You are right, I was using np.random.random() because when I was using np.random.randn(), I got the following output:
TypeError Traceback (most recent call last)
in
1 np.random.seed(2)
2 n_x, n_h, n_y = initialize_parameters_test_case()
----> 3 parameters = initialize_parameters(n_x, n_h, n_y)
4
5 print("W1 = " + str(parameters[“W1”]))

in initialize_parameters(n_x, n_h, n_y)
21 # b2 = …
22 # YOUR CODE STARTS HERE
—> 23 W1 = 0.01 *np.random.randn((n_h,n_x))
24 b1 = np.zeros((n_h,1))
25 W2 = 0.01 *np.random.randn((n_y,n_h))

mtrand.pyx in numpy.random.mtrand.RandomState.randn()

mtrand.pyx in numpy.random.mtrand.RandomState.standard_normal()

_common.pyx in numpy.random._common.cont()

TypeError: ‘tuple’ object cannot be interpreted as an integer

6

Hi @yuvalbz,

The problem lies in the way you passed in the parameters to np.random.randn(), which is tuple, W1 = 0.01 *np.random.randn((n_h,n_x)). This function expects parameters as int, not tuple. There should only be one set of (), like this: W1 = 0.01 *np.random.randn(n_h,n_x).

Here is an extract from the reference menu:

random.randn(d0 , d1 , … , dn )

Parameters:
d0, d1, …, dn int, optional

The dimensions of the returned array, must be non-negative. If no argument is given a single Python float is returned.

2 Likes
7

Thanks a lot
This was very helpful:-)