CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
y33-j3T

Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

GitHub Repository: y33-j3T/Coursera-Deep-Learning
 Path: blob/master/Improving Deep Neural Networks Hyperparameter tuning, Regularization and Optimization/week5/Regularization/testCases.py
Views: 13377
1
import numpy as np

2


3
def compute_cost_with_regularization_test_case():

4
    np.random.seed(1)

5
    Y_assess = np.array([[1, 1, 0, 1, 0]])

6
    W1 = np.random.randn(2, 3)

7
    b1 = np.random.randn(2, 1)

8
    W2 = np.random.randn(3, 2)

9
    b2 = np.random.randn(3, 1)

10
    W3 = np.random.randn(1, 3)

11
    b3 = np.random.randn(1, 1)

12
    parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2, "W3": W3, "b3": b3}

13
    a3 = np.array([[ 0.40682402,  0.01629284,  0.16722898,  0.10118111,  0.40682402]])

14
    return a3, Y_assess, parameters

15


16
def backward_propagation_with_regularization_test_case():

17
    np.random.seed(1)

18
    X_assess = np.random.randn(3, 5)

19
    Y_assess = np.array([[1, 1, 0, 1, 0]])

20
    cache = (np.array([[-1.52855314,  3.32524635,  2.13994541,  2.60700654, -0.75942115],

21
         [-1.98043538,  4.1600994 ,  0.79051021,  1.46493512, -0.45506242]]),

22
  np.array([[ 0.        ,  3.32524635,  2.13994541,  2.60700654,  0.        ],

23
         [ 0.        ,  4.1600994 ,  0.79051021,  1.46493512,  0.        ]]),

24
  np.array([[-1.09989127, -0.17242821, -0.87785842],

25
         [ 0.04221375,  0.58281521, -1.10061918]]),

26
  np.array([[ 1.14472371],

27
         [ 0.90159072]]),

28
  np.array([[ 0.53035547,  5.94892323,  2.31780174,  3.16005701,  0.53035547],

29
         [-0.69166075, -3.47645987, -2.25194702, -2.65416996, -0.69166075],

30
         [-0.39675353, -4.62285846, -2.61101729, -3.22874921, -0.39675353]]),

31
  np.array([[ 0.53035547,  5.94892323,  2.31780174,  3.16005701,  0.53035547],

32
         [ 0.        ,  0.        ,  0.        ,  0.        ,  0.        ],

33
         [ 0.        ,  0.        ,  0.        ,  0.        ,  0.        ]]),

34
  np.array([[ 0.50249434,  0.90085595],

35
         [-0.68372786, -0.12289023],

36
         [-0.93576943, -0.26788808]]),

37
  np.array([[ 0.53035547],

38
         [-0.69166075],

39
         [-0.39675353]]),

40
  np.array([[-0.3771104 , -4.10060224, -1.60539468, -2.18416951, -0.3771104 ]]),

41
  np.array([[ 0.40682402,  0.01629284,  0.16722898,  0.10118111,  0.40682402]]),

42
  np.array([[-0.6871727 , -0.84520564, -0.67124613]]),

43
  np.array([[-0.0126646]]))

44
    return X_assess, Y_assess, cache

45


46
def forward_propagation_with_dropout_test_case():

47
    np.random.seed(1)

48
    X_assess = np.random.randn(3, 5)

49
    W1 = np.random.randn(2, 3)

50
    b1 = np.random.randn(2, 1)

51
    W2 = np.random.randn(3, 2)

52
    b2 = np.random.randn(3, 1)

53
    W3 = np.random.randn(1, 3)

54
    b3 = np.random.randn(1, 1)

55
    parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2, "W3": W3, "b3": b3}

56
    

57
    return X_assess, parameters

58


59
def backward_propagation_with_dropout_test_case():

60
    np.random.seed(1)

61
    X_assess = np.random.randn(3, 5)

62
    Y_assess = np.array([[1, 1, 0, 1, 0]])

63
    cache = (np.array([[-1.52855314,  3.32524635,  2.13994541,  2.60700654, -0.75942115],

64
           [-1.98043538,  4.1600994 ,  0.79051021,  1.46493512, -0.45506242]]), np.array([[ True, False,  True,  True,  True],

65
           [ True,  True,  True,  True, False]], dtype=bool), np.array([[ 0.        ,  0.        ,  4.27989081,  5.21401307,  0.        ],

66
           [ 0.        ,  8.32019881,  1.58102041,  2.92987024,  0.        ]]), np.array([[-1.09989127, -0.17242821, -0.87785842],

67
           [ 0.04221375,  0.58281521, -1.10061918]]), np.array([[ 1.14472371],

68
           [ 0.90159072]]), np.array([[ 0.53035547,  8.02565606,  4.10524802,  5.78975856,  0.53035547],

69
           [-0.69166075, -1.71413186, -3.81223329, -4.61667916, -0.69166075],

70
           [-0.39675353, -2.62563561, -4.82528105, -6.0607449 , -0.39675353]]), np.array([[ True, False,  True, False,  True],

71
           [False,  True, False,  True,  True],

72
           [False, False,  True, False, False]], dtype=bool), np.array([[ 1.06071093,  0.        ,  8.21049603,  0.        ,  1.06071093],

73
           [ 0.        ,  0.        ,  0.        ,  0.        ,  0.        ],

74
           [ 0.        ,  0.        ,  0.        ,  0.        ,  0.        ]]), np.array([[ 0.50249434,  0.90085595],

75
           [-0.68372786, -0.12289023],

76
           [-0.93576943, -0.26788808]]), np.array([[ 0.53035547],

77
           [-0.69166075],

78
           [-0.39675353]]), np.array([[-0.7415562 , -0.0126646 , -5.65469333, -0.0126646 , -0.7415562 ]]), np.array([[ 0.32266394,  0.49683389,  0.00348883,  0.49683389,  0.32266394]]), np.array([[-0.6871727 , -0.84520564, -0.67124613]]), np.array([[-0.0126646]]))

79


80


81
    return X_assess, Y_assess, cache

82
    

83