CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
amanchadha

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: amanchadha/coursera-deep-learning-specialization
 Path: blob/master/C1 - Neural Networks and Deep Learning/Week 3/Planar data classification with one hidden layer/testCases_v2.py
Views: 4798
1
import numpy as np

2


3
def layer_sizes_test_case():

4
    np.random.seed(1)

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

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

7
    return X_assess, Y_assess

8


9
def initialize_parameters_test_case():

10
    n_x, n_h, n_y = 2, 4, 1

11
    return n_x, n_h, n_y

12


13


14
def forward_propagation_test_case():

15
    np.random.seed(1)

16
    X_assess = np.random.randn(2, 3)

17
    b1 = np.random.randn(4,1)

18
    b2 = np.array([[ -1.3]])

19


20
    parameters = {'W1': np.array([[-0.00416758, -0.00056267],

21
        [-0.02136196,  0.01640271],

22
        [-0.01793436, -0.00841747],

23
        [ 0.00502881, -0.01245288]]),

24
     'W2': np.array([[-0.01057952, -0.00909008,  0.00551454,  0.02292208]]),

25
     'b1': b1,

26
     'b2': b2}

27


28
    return X_assess, parameters

29


30
def compute_cost_test_case():

31
    np.random.seed(1)

32
    Y_assess = (np.random.randn(1, 3) > 0)

33
    parameters = {'W1': np.array([[-0.00416758, -0.00056267],

34
        [-0.02136196,  0.01640271],

35
        [-0.01793436, -0.00841747],

36
        [ 0.00502881, -0.01245288]]),

37
     'W2': np.array([[-0.01057952, -0.00909008,  0.00551454,  0.02292208]]),

38
     'b1': np.array([[ 0.],

39
        [ 0.],

40
        [ 0.],

41
        [ 0.]]),

42
     'b2': np.array([[ 0.]])}

43


44
    a2 = (np.array([[ 0.5002307 ,  0.49985831,  0.50023963]]))

45
    

46
    return a2, Y_assess, parameters

47


48
def backward_propagation_test_case():

49
    np.random.seed(1)

50
    X_assess = np.random.randn(2, 3)

51
    Y_assess = (np.random.randn(1, 3) > 0)

52
    parameters = {'W1': np.array([[-0.00416758, -0.00056267],

53
        [-0.02136196,  0.01640271],

54
        [-0.01793436, -0.00841747],

55
        [ 0.00502881, -0.01245288]]),

56
     'W2': np.array([[-0.01057952, -0.00909008,  0.00551454,  0.02292208]]),

57
     'b1': np.array([[ 0.],

58
        [ 0.],

59
        [ 0.],

60
        [ 0.]]),

61
     'b2': np.array([[ 0.]])}

62


63
    cache = {'A1': np.array([[-0.00616578,  0.0020626 ,  0.00349619],

64
         [-0.05225116,  0.02725659, -0.02646251],

65
         [-0.02009721,  0.0036869 ,  0.02883756],

66
         [ 0.02152675, -0.01385234,  0.02599885]]),

67
  'A2': np.array([[ 0.5002307 ,  0.49985831,  0.50023963]]),

68
  'Z1': np.array([[-0.00616586,  0.0020626 ,  0.0034962 ],

69
         [-0.05229879,  0.02726335, -0.02646869],

70
         [-0.02009991,  0.00368692,  0.02884556],

71
         [ 0.02153007, -0.01385322,  0.02600471]]),

72
  'Z2': np.array([[ 0.00092281, -0.00056678,  0.00095853]])}

73
    return parameters, cache, X_assess, Y_assess

74


75
def update_parameters_test_case():

76
    parameters = {'W1': np.array([[-0.00615039,  0.0169021 ],

77
        [-0.02311792,  0.03137121],

78
        [-0.0169217 , -0.01752545],

79
        [ 0.00935436, -0.05018221]]),

80
 'W2': np.array([[-0.0104319 , -0.04019007,  0.01607211,  0.04440255]]),

81
 'b1': np.array([[ -8.97523455e-07],

82
        [  8.15562092e-06],

83
        [  6.04810633e-07],

84
        [ -2.54560700e-06]]),

85
 'b2': np.array([[  9.14954378e-05]])}

86


87
    grads = {'dW1': np.array([[ 0.00023322, -0.00205423],

88
        [ 0.00082222, -0.00700776],

89
        [-0.00031831,  0.0028636 ],

90
        [-0.00092857,  0.00809933]]),

91
 'dW2': np.array([[ -1.75740039e-05,   3.70231337e-03,  -1.25683095e-03,

92
          -2.55715317e-03]]),

93
 'db1': np.array([[  1.05570087e-07],

94
        [ -3.81814487e-06],

95
        [ -1.90155145e-07],

96
        [  5.46467802e-07]]),

97
 'db2': np.array([[ -1.08923140e-05]])}

98
    return parameters, grads

99


100
def nn_model_test_case():

101
    np.random.seed(1)

102
    X_assess = np.random.randn(2, 3)

103
    Y_assess = (np.random.randn(1, 3) > 0)

104
    return X_assess, Y_assess

105


106
def predict_test_case():

107
    np.random.seed(1)

108
    X_assess = np.random.randn(2, 3)

109
    parameters = {'W1': np.array([[-0.00615039,  0.0169021 ],

110
        [-0.02311792,  0.03137121],

111
        [-0.0169217 , -0.01752545],

112
        [ 0.00935436, -0.05018221]]),

113
     'W2': np.array([[-0.0104319 , -0.04019007,  0.01607211,  0.04440255]]),

114
     'b1': np.array([[ -8.97523455e-07],

115
        [  8.15562092e-06],

116
        [  6.04810633e-07],

117
        [ -2.54560700e-06]]),

118
     'b2': np.array([[  9.14954378e-05]])}

119
    return parameters, X_assess

120


121