吴恩达深度学习第一课-第四周课后编程题

注：在完成编程题前，要先下载四个重要文件（缺一不可）：

• testCases.py

• dnn_utils.py

• lr_utils.py

• dataset

下载链接：第四周编程题资料，提取码：kehg

完整代码如下：

注：

• 题目以及每一小题的提示均以#注释方式在代码中呈现

• 逐小题进行编写和运行效果更佳，即模仿Jupyter Notebook的代码块形式进行编写和运行

import time
import numpy as np
import h5py
import scipy
from PIL import Image
from scipy import ndimage
from lr_utils import *
import matplotlib.pyplot as plt
from testCases import *
from dnn_utils import sigmoid, sigmoid_backward, relu, relu_backward  # provide some necessary functions for this notebook

plt.rcParams['figure.figsize'] = (5.0, 4.0)  # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

np.random.seed(1)


# Exercise1: Create and initialize the parameters of the 2-layer neural network
"""
Instructions:
    - The model's structure is:LINEAR -> RULU -> LINEAR ->SIGMOID
    - Use random initialization for the weight matrices.Use np.random.randn(shape)*0.01 with the correct shape
    - Use zero initialization for the biases. Use np.zeros(shape)
"""
def initialize_parameters(n_x, n_h, n_y):
    """
    Argument:
    n_x -- size of the input layer
    n_h -- size of the hidden layer
    n_y -- size of the output layer

    Returns:
    parameters -- python dictionary containing your parameters:
                    W1 -- weight matrix of shape (n_h, n_x)
                    b1 -- bias vector of shape (n_h, 1)
                    W2 -- weight matrix of shape (n_y, n_h)
                    b2 -- bias vector of shape (n_y, 1)
    """

    np.random.seed(1)

    #  START CODE HERE (≈ 4 lines of code)
    W1 = np.random.randn(n_h, n_x) * 0.01
    b1 = np.zeros(shape=(n_h, 1))
    W2 = np.random.randn(n_y, n_h) * 0.01
    b2 = np.zeros(shape=(n_y, 1))
    # END CODE HERE

    assert (W1.shape == (n_h, n_x))
    assert (b1.shape == (n_h, 1))
    assert (W2.shape == (n_y, n_h))
    assert (b2.shape == (n_y, 1))

    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters


# test for 'initialize_parameters'
print('========== test for initialize_parameters ==========')
parameters = initialize_parameters(2, 2, 1)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))


# Exercise2: Implement initialization for an L-layer Neural Network
"""
Instructions:
    - The model's structure is [LINEAR -> RELU] * (L-1) -> LINEAR -> SIGMOID. I.e., it has L-1 layers using a ReLU 
    activation function followed by an output layer with a sigmoid activation function.
    - Use random initialization for the weight matrices. Use np.random.rand(shape) * 0.01.
    - Use zeros initialization for the biases. Use np.zeros(shape).
    -We will store n^[l], the number of units in different layers, in a variable layer_dims. For example, the layer_dims
    for the "Planar Data classification model" from last week would have been [2,4,1]: There were two inputs, one hidden
    layer with 4 hidden units, and an output layer with 1 output unit. Thus means W1's shape was (4,2), b1 was (4,1), W2
    was (1,4) and b2 was (1,1). Now you will generalize this to L layers!
    - Here is the implementation for L=1 (one layer neural network). It should inspire you to implement the general case
    (L-layer neural network).
    if L == 1:
        parameters["W" + str(L)] = np.random.randn(layer_dims[1], layer_dims[0]) * 0.01
        parameters["b" + str(L)] = np.zeros((layer_dims[1], 1))
"""
def initialize_parameters_deep(layer_dims):
    """
    Arguments:
    layer_dims -- python array (list) containing the dimensions of each layer in our network

    Returns:
    parameters -- python dictionary containing your parameters "W1", "b1", ..., "WL", "bL":
                    Wl -- weight matrix of shape (layer_dims[l], layer_dims[l-1])
                    bl -- bias vector of shape (layer_dims[l], 1)
    """

    np.random.seed(3)
    parameters = {}
    L = len(layer_dims)  # number of layers in the network

    for l in range(1, L):
        # START CODE HERE (≈ 2 lines of code)
        parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l-1]) * 0.01
        parameters['b' + str(l)] = np.zeros((layer_dims[l], 1))
        # END CODE HERE

        assert (parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l - 1]))
        assert (parameters['b' + str(l)].shape == (layer_dims[l], 1))

    return parameters


# test for initialize_parameters_deep
print('========== test for initialize_parameters_deep ==========')
parameters = initialize_parameters_deep([5, 4, 3])
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))


"""
You will complete three functions in this order:
    - LINEAR
    - LINEAR -> ACTIVATION where ACTIVATION will be either ReLU or Sigmoid.
    - [LINEAR -> RELU] * (L-1) -> LINEAR -> SIGMOID (whole model)
"""
# Exercise3: Build the linear part of forward propagation
"""
Reminder: The mathematical representation of this unit is Z^[l] = W^[l]A^[l-1] + b^[l]. You may also find np.dot() useful.
If your dimensions don't match, printing W.shape may help.
"""
def linear_forward(A, W, b):
    """
    Implement the linear part of a layer's forward propagation.

    Arguments:
    A -- activations from previous layer (or input data): (size of previous layer, number of examples)
    W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
    b -- bias vector, numpy array of shape (size of the current layer, 1)

    Returns:
    Z -- the input of the activation function, also called pre-activation parameter
    cache -- a python dictionary containing "A", "W" and "b" ; stored for computing the backward pass efficiently
    """

    # START CODE HERE(≈ 1 line of code)
    Z = np.dot(W, A) + b
    # END CODE HERE

    assert (Z.shape == (W.shape[0], A.shape[1]))
    cache = (A, W, b)

    return Z, cache


# test for linear_forward
print('========== test for linear_forward ==========')
A, W, b = linear_forward_test_case()
Z, linear_cache = linear_forward(A, W, b)
print("Z = " + str(Z))


# Exercise4: Implement the forward propagation of the LINEAR->ACTIVATION layer. Mathematical relation is:
# A^[l] = g(Z^[l])=g(W^[l]A^[l-1] + b^[l] where the activation "g" can be sigmoid() or relu(). Use linear_forward() and
# the correct activation function.
def linear_activation_forward(A_prev, W, b, activation):
    """
    Implement the forward propagation for the LINEAR->ACTIVATION layer

    Arguments:
    A_prev -- activations from previous layer (or input data): (size of previous layer, number of examples)
    W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
    b -- bias vector, numpy array of shape (size of the current layer, 1)
    activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu"

    Returns:
    A -- the output of the activation function, also called the post-activation value
    cache -- a python dictionary containing "linear_cache" and "activation_cache";
             stored for computing the backward pass efficiently
    """

    if activation == "sigmoid":
        # Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
        # START CODE HERE (≈ 2 lines of code)
        Z, linear_cache = linear_forward(A_prev, W, b)
        A, activation_cache = sigmoid(Z)
        # END CODE HERE

    elif activation == 'relu':
        # Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
        # START CODE HERE (≈ 2 lines of code)
        Z, linear_cache = linear_forward(A_prev, W, b)
        A, activation_cache = relu(Z)
        # END CODE HERE

    assert(A.shape == (W.shape[0], A_prev.shape[1]))
    cache = (linear_cache, activation_cache)

    return A, cache


# test for linear_activation_forward
print('========== test for linear_activation_forward ==========')
A_prev, W, b = linear_activation_forward_test_case()

A, linear_activation_cache = linear_activation_forward(A_prev, W, b, activation="sigmoid")
print("With sigmoid: A = " + str(A))

A, linear_activation_cache = linear_activation_forward(A_prev, W, b, activation="relu")
print("With ReLU: A = " + str(A))


# Exercise5: Implement the forward propagation of the above model.
"""
Instruction: In the code below, the variable AL will denote A^[L]=sigmoid(Z^[L])=sigmoid(W^[L]A^[L-1]+b^[L]). (This is 
sometimes also called Yhat, i.e.)

Tips:
    - Use the functions you had previously written
    - Use a for loop to replicate [LINEAR->RELU] (L-1) times
    - Don't forget to keep track of the caches in the "caches" list. To add a new value c to a list, you can use 
    list.append(c).
"""
def L_model_forward(X, parameters):
    """
    Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation

    Arguments:
    X -- data, numpy array of shape (input size, number of examples)
    parameters -- output of initialize_parameters_deep()

    Returns:
    AL -- last post-activation value
    caches -- list of caches containing:
                every cache of linear_relu_forward() (there are L-1 of them, indexed from 0 to L-2)
                the cache of linear_sigmoid_forward() (there is one, indexed L-1)
    """
    caches = []
    A = X
    L = len(parameters) // 2  # number of layers in the neural network

    # Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
    for l in range(1, L):
        A_prev = A
        # START CODE HERE (≈ 2 lines of code)
        A, cache = linear_activation_forward(A_prev,
                                             parameters['W' + str(l)],
                                             parameters['b' + str(l)],
                                             activation='relu')
        caches.append(cache)
        # END CODE HERE

    # Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
    # START CODE HERE (≈ 2 lines of code)
    AL, cache = linear_activation_forward(A,
                                          parameters['W' + str(L)],
                                          parameters['b' + str(L)],
                                          activation='sigmoid'
                                          )
    caches.append(cache)
    # END CODE HERE

    assert(AL.shape == (1, X.shape[1]))

    return AL, caches


# test for L_model_forward
print('========== test for L_model_forward ==========')
X, parameters = L_model_forward_test_case()
AL, caches = L_model_forward(X, parameters)
print("AL = " + str(AL))
print("Length of caches list = " + str(len(caches)))


# Exercise6: Compute the cross-entropy cost
def compute_cost(AL, Y):
    """
    Implement the cost function defined by equation (7).

    Arguments:
    AL -- probability vector corresponding to your label predictions, shape (1, number of examples)
    Y -- true "label" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples)

    Returns:
    cost -- cross-entropy cost
    """

    m = Y.shape[1]

    # Compute loss from aL and y.
    # START CODE HERE (≈ 1 lines of code)
    cost = (-1/m) * np.sum(np.multiply(Y, np.log(AL)) + np.multiply(1-Y, np.log(1-AL)))
    # END CODE HERE

    cost = np.squeeze(cost)  # To make sure your cost's shape is what we expect (e.g.this turns[[17]] into 17).
    assert (cost.shape == ())

    return cost


# test for compute_cost
print('========== test for compute_cost ==========')
Y, AL = compute_cost_test_case()
print("cost = " + str(compute_cost(AL, Y)))


# Exercise7: Implement linear_backward()
def linear_backward(dZ, cache):
    """
    Implement the linear portion of backward propagation for a single layer (layer l)

    Arguments:
    dZ -- Gradient of the cost with respect to the linear output (of current layer l)
    cache -- tuple of values (A_prev, W, b) coming from the forward propagation in the current layer

    Returns:
    dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev
    dW -- Gradient of the cost with respect to W (current layer l), same shape as W
    db -- Gradient of the cost with respect to b (current layer l), same shape as b
    """
    A_prev, W, b = cache
    m = A_prev.shape[1]

    # START CODE HERE (≈ 3 lines of code)
    dW = (1/m) * np.dot(dZ, cache[0].T)
    db = (1/m) * np.sum(dZ)
    dA_prev = np.dot(cache[1].T, dZ)
    # END CODE HERE

    assert (dA_prev.shape == A_prev.shape)
    assert (dW.shape == W.shape)
    assert (isinstance(db, float))

    return dA_prev, dW, db


# test for linear_backward
print('========== test for linear_backward ==========')
dZ, linear_cache = linear_backward_test_case()

dA_prev, dW, db = linear_backward(dZ, linear_cache)
print("dA_prev = " + str(dA_prev))
print("dW = " + str(dW))
print("db = " + str(db))


# Exercise8: Implement the backpropagation for the LINEAR->ACTIVATION layer
def linear_activation_backward(dA, cache, activation):
    """
    Implement the backward propagation for the LINEAR->ACTIVATION layer.

    Arguments:
    dA -- post-activation gradient for current layer l
    cache -- tuple of values (linear_cache, activation_cache) we store for computing backward propagation efficiently
    activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu"

    Returns:
    dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev
    dW -- Gradient of the cost with respect to W (current layer l), same shape as W
    db -- Gradient of the cost with respect to b (current layer l), same shape as b
    """
    linear_cache, activation_cache = cache

    if activation == 'relu':
        # START CODE HERE (≈ 2 lines of code)
        dZ = relu_backward(dA, activation_cache)
        # END CODE HERE

    elif activation == 'sigmoid':
        # START CODE HERE (≈ 2 lines of code)
        dZ = sigmoid_backward(dA, activation_cache)
        # END CODE HERE

    # Shorten the code
    dA_prev, dW, db = linear_backward(dZ, linear_cache)

    return dA_prev, dW, db


# test for linear_activation_backward
print('========== test for linear_activation_backward ==========')
AL, linear_activation_cache = linear_activation_backward_test_case()

dA_prev, dW, db = linear_activation_backward(AL, linear_activation_cache, activation="sigmoid")
print("sigmoid:")
print("dA_prev = " + str(dA_prev))
print("dW = " + str(dW))
print("db = " + str(db) + "\n")

dA_prev, dW, db = linear_activation_backward(AL, linear_activation_cache, activation="relu")
print("relu:")
print("dA_prev = "+ str(dA_prev))
print("dW = " + str(dW))
print("db = " + str(db))


# Exercise9: Implement backpropagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID model.
def L_model_backward(AL, Y, caches):
    """
    Implement the backward propagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group

    Arguments:
    AL -- probability vector, output of the forward propagation (L_model_forward())
    Y -- true "label" vector (containing 0 if non-cat, 1 if cat)
    caches -- list of caches containing:
                every cache of linear_activation_forward() with "relu" (it's caches[l], for l in range(L-1) i.e l = 0...L-2)
                the cache of linear_activation_forward() with "sigmoid" (it's caches[L-1])

    Returns:
    grads -- A dictionary with the gradients
             grads["dA" + str(l)] = ...
             grads["dW" + str(l)] = ...
             grads["db" + str(l)] = ...
    """
    grads = {}
    L = len(caches)  # the number of layers
    m = AL.shape[1]
    Y = Y.reshape(AL.shape)  # after this line, Y is the same shape as AL

    # Initializing the backpropagation
    # START CODE HERE (1 line of code)
    dAL = -(np.divide(Y, AL) - np.divide(1-Y, 1-AL))
    # END CODE HERE
    # Lth layer (SIGMOID -> LINEAR) gradients. Inputs:"AL, Y, caches". Outputs: "grads["dAL"], grads["dWL"], grads["dbL"]
    # START CODE HERE (approx. 2 lines)
    current_cache = caches[-1]
    grads["dA" + str(L)], grads["dW" + str(L)], grads["db" + str(L)] = linear_activation_backward(dAL, current_cache, "sigmoid")
    # END CODE HERE

    for l in reversed(range(L-1)):
        # lth layer: (RELU->LINEAR) gradients
        # Inputs:"grads["dA" + str(l + 2)], caches". Outputs: "grads["dA" + str(l + 1)] , grads["dW" + str(l + 1)] , grads["db" + str(l + 1)]
        # START CODE HERE (approx. 5 lines)
        current_cache = caches[l]
        dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(l+2)], current_cache, "relu")
        grads["dA" + str(l+1)] = dA_prev_temp
        grads["dW" + str(l+1)] = dW_temp
        grads["db" + str(l+1)] = db_temp
        # END CODE HERE

    return grads


# test for L_model_backward
print('========== test for L_model_backward ==========')
AL, Y_assess, caches = L_model_backward_test_case()
grads = L_model_backward(AL, Y_assess, caches)
print("dW1 = " + str(grads["dW1"]))
print("db1 = " + str(grads["db1"]))
print("dA1 = " + str(grads["dA1"]))


# Exercise10: Implement update_parameters() to update your parameters using gradient descent
def update_parameters(parameters, grads, learning_rate):
    """
    Update parameters using gradient descent

    Arguments:
    parameters -- python dictionary containing your parameters
    grads -- python dictionary containing your gradients, output of L_model_backward

    Returns:
    parameters -- python dictionary containing your updated parameters
                  parameters["W" + str(l)] = ...
                  parameters["b" + str(l)] = ...
    """
    L = len(parameters) // 2  # number of layers in the neural network

    # Update rule for each parameter. Use a for loop.
    # START CODE HERE (≈ 3 lines of code)
    for l in range(L):
        parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - learning_rate * grads["dW" + str(l+1)]
        parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - learning_rate * grads["db" + str(l+1)]

    return parameters


# test for update_parameters
print("========== test for update_parameters ==========")
parameters, grads = update_parameters_test_case()
parameters = update_parameters(parameters, grads, 0.1)

print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))


# Load the data
train_x_orig, train_y, test_x_orig, test_y, classes = load_dataset()

# Example of a picture
# index = 22
# plt.imshow(train_x_orig[index])
# print("y = " + str(train_y[0, index]) + ". It's a " + classes[train_y[0, index]].decode("utf-8") + " picture.")
# plt.show()

# Reshape the training and test examples
train_x_flatten = train_x_orig.reshape(train_x_orig.shape[0], -1).T  # The "-1" makes reshape flatten the remaining dimensions
test_x_flatten = test_x_orig.reshape(test_x_orig.shape[0], -1).T  # The "-1" makes reshape flatten the remaining dimensions

# Standardize data to have feature values between 0 and 1
train_x = train_x_flatten / 255
test_x = test_x_flatten / 255

print("train_x's shape: " + str(train_x.shape))
print("test_x's shape: " + str(test_x.shape))


# Two-layer neural network
# CONSTANTS DEFINING THE MODEL
n_x = 12288     # num_px * num_px * 3
n_h = 7
n_y = 1
layers_dims = (n_x, n_h, n_y)


def two_layer_model(X, Y, layers_dims, learning_rate=0.0075, num_iterations=3000, print_cost=False, isPlot=True):
    """
    Implements a two-layer neural network: LINEAR->RELU->LINEAR->SIGMOID.

    Arguments:
    X -- input data, of shape (n_x, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
    layers_dims -- dimensions of the layers (n_x, n_h, n_y)
    num_iterations -- number of iterations of the optimization loop
    learning_rate -- learning rate of the gradient descent update rule
    print_cost -- If set to True, this will print the cost every 100 iterations

    Returns:
    parameters -- a dictionary containing W1, W2, b1, and b2
    """
    np.random.seed(1)
    grads = {}
    costs = []
    (n_x, n_h, n_y) = layers_dims

    # Initialize parameters dictionary
    # START CODE HERE
    parameters = initialize_parameters(n_x, n_h, n_y)
    # END CODE HERE

    # Get W1, b1, W2 and b2 from the dictionary parameters.
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    # Loop (gradient descent)
    for i in range(num_iterations):
        # Forward propagation: LINEAR -> RELU -> LINEAR -> SIGMOID. Inputs: "X, W1, b1". Output: "A1, cache1, A2, cache2".
        # START CODE HERE (≈ 2 lines of code)
        A1, cache1 = linear_activation_forward(X, W1, b1, 'relu')
        A2, cache2 = linear_activation_forward(A1, W2, b2, 'sigmoid')
        # END CODE HERE

        # Compute cost
        # START CODE HERE
        cost = compute_cost(A2, Y)
        # END CODE HERE

        # Initializing backward propagation
        dA2 = -(np.divide(Y, A2) - np.divide(1-Y, 1-A2))

        # Backward propagation. Inputs: "dA2, cache2, cache1". Outputs: "dA1, dW2, db2; also dA0 (not used), dW1, db1".
        # START CODE HERE  (≈ 2 lines of code)
        dA1, dW2, db2 = linear_activation_backward(dA2, cache2, 'sigmoid')
        dA0, dW1, db1 = linear_activation_backward(dA1, cache1, 'relu')

        # Set grads['dWl'] to dW1, grads['db1'] to db1, grads['dW2'] to dW2, grads['db2'] to db2
        grads['dW1'] = dW1
        grads['db1'] = db1
        grads['dW2'] = dW2
        grads['db2'] = db2

        # Update parameters
        # START CODE HERE
        parameters = update_parameters(parameters, grads, learning_rate)
        # END CODE HERE

        # Retrieve W1, b1, W2, b2 from parameters
        W1 = parameters['W1']
        b1 = parameters['b1']
        W2 = parameters['W2']
        b2 = parameters['b2']

        # Print the cost every 100 training example
        if i % 100 == 0:
            costs.append(cost)
            if print_cost:
                print("Cost after iteration {} : {}".format(i, np.squeeze(cost)))

    # Plot the cost
    if isPlot:
        plt.plot(np.squeeze(costs))
        plt.ylabel('cost')
        plt.xlabel('iteration (per tens)')
        plt.title("Learning rate = " + str(learning_rate))
        plt.show()

    return parameters


parameters = two_layer_model(train_x, train_y, layers_dims=(n_x, n_h, n_y), num_iterations=2500, print_cost=True)


# function for predicting
def predict(X, y, parameters):
    """
    :param X: test set
    :param y: labels
    :param parameters: W,b for each layer
    :return p: prediction of test set
    """
    m = X.shape[1]
    n = len(parameters) // 2
    p = np.zeros((1,m))

    # forward propagation
    Yhat, caches = L_model_forward(X, parameters)

    for i in range(Yhat.shape[1]):
        if Yhat[0, i] > 0.5:
            p[0, i] = 1
        else:
            p[0, i] = 0

    print("Accuracy: " + str(float(np.sum((p == y))/m)))

    return p


# prediction of the 2-layer
predictions_test = predict(test_x, test_y, parameters)


# L-layer Neural Network
# CONSTANTS
layers_dims = [12288, 20, 7, 5, 1]  # Assume that it's a 5-layer network


def L_layer_model(X, Y, layers_dims, learning_rate=0.0075, num_iterations=3000, print_cost=False, isPlot=True):
    """
    Implements a L-layer neural network: [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID.

    Arguments:
    X -- data, numpy array of shape (num_px * num_px * 3, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
    layers_dims -- list containing the input size and each layer size, of length (number of layers + 1).
    learning_rate -- learning rate of the gradient descent update rule
    num_iterations -- number of iterations of the optimization loop
    print_cost -- if True, it prints the cost every 100 steps
    isPlot -- print the graph of error or not

    Returns:
    parameters -- parameters learnt by the model. They can then be used to predict.
    """
    np.random.seed(1)
    costs = []

    parameters = initialize_parameters_deep(layers_dims)

    for i in range(num_iterations):
        # Forward propagation
        AL, caches = L_model_forward(X, parameters)
        # Compute cost
        cost = compute_cost(AL, Y)
        # Backward propagation
        grads = L_model_backward(AL, Y, caches)
        # Update parameters
        parameters = update_parameters(parameters, grads, learning_rate)

        if i % 100 == 0:
            costs.append(cost)
            if print_cost:
                print("Cost after iteration {} : {}".format(i, np.squeeze(cost)))

    if isPlot:
        plt.plot(np.squeeze(costs))
        plt.ylabel('cost')
        plt.xlabel('iterations (per tens)')
        plt.title("Learning rate = " + str(learning_rate))
        plt.show()

    return parameters


parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations=2500, print_cost=True)

pred_test = predict(test_x, test_y, parameters)


# wrongly labeled images
def print_mislabeled_images(classes, X, y, p):
    """
    :param X: data set
    :param y: label
    :param p: prediction
    """
    a = p + y
    mislabeled_indices = np.asarray(np.where(a == 1))
    plt.rcParams['figure.figsize'] = (40.0, 40.0)  # set default size of plots
    num_images = len(mislabeled_indices[0])
    for i in range(num_images):
        index = mislabeled_indices[1][i]

        plt.subplot(2, num_images, i+1)
        plt.imshow(X[:, index].reshape(64, 64, 3), interpolation='nearest')
        plt.axis('off')
        plt.title("Prediction: " + classes[int(p[0, index])].decode("utf-8") + "\n Class: " + classes[y[0, index]].decode("utf-8"))


print_mislabeled_images(classes, test_x, test_y, pred_test)


# 选择一张自己的图片用刚才构建的网络进行测试
my_image = "my_image.jpg"  # change this to the name of your image file
my_label_y = [1]

fname = "images/" + my_image
image = np.array(ndimage.imread(fname, flatten=False))
my_image = scipy.misc.imresize(image, size=(num_px, num_px)).reshape((num_px*num_px*3, 1))
my_predicted_image = predict(my_image, my_label_y, parameters)

plt.imshow(image)
print("y = " + str(np.squeeze(my_predicted_image)) + ", your L-layer model predicts a \"" + classes[int(np.squeeze(my_predicted_image))].decode("utf-8") + "\" picture.")