吴恩达 深度学习 第一门课 神经网络和深度学习 使用浅层神经网络实现平面数据分类

用逻辑回归对平面的数据进行分类

• 首先画出图像
  本次需要的文件：点击下载
  
• 画图代码如下：

# -*- encoding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets


np.random.seed(1) # set a seed so that the results are consistent

def load_planar_dataset():
    np.random.seed(1)
    m = 400
    N = int(m / 2)
    D = 2
    X = np.zeros((m, D))
    Y = np.zeros((m, 1), dtype='uint8')
    a = 4
    for j in range(2):
        ix = range(N * j, N * (j + 1))
        t = np.linspace(j * 3.12, (j + 1) * 3.12, N) + np.random.randn(N) * 0.2  # theta
        r = a * np.sin(4 * t) + np.random.randn(N) * 0.2  # radius
        X[ix] = np.c_[r * np.sin(t), r * np.cos(t)]    # 按行连接俩个矩阵
        Y[ix] = j

    X = X.T
    Y = Y.T

    return X, Y

if __name__ == '__main__':
    X, Y = load_planar_dataset()
    plt.scatter(X[0, :], X[1, :], c=np.squeeze(Y), s=40, cmap=plt.cm.Spectral)
    plt.show()

• 接着用逻辑回归来分类
  
  • 准确度如下：
    Accuracy of logistic regression: 47 % (percentage of correctly labelled datapoints)
    源码：

# -*- encoding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets


np.random.seed(1) # set a seed so that the results are consistent

def load_planar_dataset():
    np.random.seed(1)
    m = 400
    N = int(m / 2)
    D = 2
    X = np.zeros((m, D))
    Y = np.zeros((m, 1), dtype='uint8')
    a = 4
    for j in range(2):
        ix = range(N * j, N * (j + 1))
        t = np.linspace(j * 3.12, (j + 1) * 3.12, N) + np.random.randn(N) * 0.2  # theta
        r = a * np.sin(4 * t) + np.random.randn(N) * 0.2  # radius
        X[ix] = np.c_[r * np.sin(t), r * np.cos(t)]    # 按行连接俩个矩阵
        Y[ix] = j

    X = X.T
    Y = Y.T

    return X, Y






if __name__ == '__main__':
    X, Y = load_planar_dataset()
    plt.scatter(X[0, :], X[1, :], c=np.squeeze(Y), s=40, cmap=plt.cm.Spectral)
    clf = sklearn.linear_model.LogisticRegressionCV()
    clf.fit(X.T, Y.T)
    plot_decision_boundary(lambda x: clf.predict(x), X, np.squeeze(Y))
    LR_predictions = clf.predict(X.T)
    print('Accuracy of logistic regression: %d ' % float(
        (np.dot(Y, LR_predictions) + np.dot(1 - Y, 1 - LR_predictions)) / float(Y.size) * 100) +
          '% ' + "(percentage of correctly labelled datapoints)")

    plt.show()

用神经网络训练一个模型

• 定义神经网络的结构

Exercise: Define three variables:

• n_x: the size of the input layer
• n_h: the size of the hidden layer (set this to 4)
• n_y: the size of the output layer

def layer_size(X, Y):
    n_x = X.shape[0]
    n_h = 4
    n_y = Y.shape[0]
    return (n_x, n_h, n_y)

• 初始化模型参数

Exercise: Implement the function initialize_parameters().

def initialize_parameters(n_x, n_h, n_y):
    np.random.seed(2)
    W1 = np.random.randn(n_h, n_x)
    b1 = np.zeros((n_h, 1))
    W2 = np.random.randn(n_y, n_h)
    b2 = np.zeros((n_y, 1))
    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters

• 循环

Question: Implement forward_propagation().

def forward_propagation(X, parameters):
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    Z1 = np.dot(W1, X) + b1
    A1 = np.tanh(Z1)
    Z2 = np.dot(W2, A1) + b2
    A2 = sigmoid(Z2)

    assert (A2.shape == (1, X.shape[1]))

    cache = {"Z1": Z1,
             "A1": A1,
             "Z2": Z2,
             "A2": A2}

    return A2, cache

Exercise: Implement compute_cost() to compute the value of the cost JJ.

def compute_cost(A2, Y, parameters):
    m = Y.shape[1]
    logprobs = np.multiply(np.log(A2), Y) + np.multiply(np.log(1-A2), (1-Y))
    cost = (-1.0 / m) * np.sum(logprobs)
    cost = np.squeeze(cost)
    return cost

def backward_propagation(parameters, cache, X, Y):
    m = X.shape[1]
    W1 = parameters["W1"]
    W2 = parameters["W2"]
    A1 = cache["A1"]
    A2 = cache["A2"]
    dZ2 = A2 - Y
    dW2 = (1.0 / m) * np.dot(dZ2, A1.T)
    db2 = (1.0 / m) * np.sum(dZ2, axis=1, keepdims=True)
    dZ1 = np.dot(W2.T, dZ2) * (1 - np.power(A1, 2))
    dW1 = 1.0 / m * np.dot(dZ1, X.T)
    db1 = 1.0 / m * np.sum(dZ1, axis=1, keepdims=True)
    grads = {"dW1": dW1,
             "db1": db1,
             "dW2": dW2,
             "db2": db2}

    return grads

Question: Implement the function backward_propagation().

def update_parameters(parameters, grads, learning_rate=1.2):
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    dW1 = grads["dW1"]
    db1 = grads["db1"]
    dW2 = grads["dW2"]
    db2 = grads["db2"]

    W1-= learning_rate * dW1
    b1 -= learning_rate * db1
    W2 -= learning_rate * dW2
    b2 -= learning_rate * db2

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

    return parameters

• 集成上述于nn_model()

Question: Build your neural network model in nn_model().

def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False):
    np.random.seed(3)
    n_x = layer_size(X, Y)[0]
    n_y = layer_size(X, Y)[2]

    parameters = initialize_parameters(n_x, n_h, n_y)
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    for i in range(num_iterations):
        A2, cache = forward_propagation(X, parameters)
        cost = compute_cost(A2, Y, parameters)
        grads = backward_propagation(parameters, cache, X, Y)
        parameters = update_parameters(parameters, grads, learning_rate=1.2)
        if print_cost and i % 100 == 0:
            print("Cost after iteration %i:%f"%(i, cost))
    return parameters

• 预测

Question: Use your model to predict by building predict(). Use forward propagation to predict results.

# -*- encoding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets


np.random.seed(1) # set a seed so that the results are consistent

def load_planar_dataset():
    np.random.seed(1)
    m = 400
    N = int(m / 2)
    D = 2
    X = np.zeros((m, D))
    Y = np.zeros((m, 1), dtype='uint8')
    a = 4
    for j in range(2):
        ix = range(N * j, N * (j + 1))
        t = np.linspace(j * 3.12, (j + 1) * 3.12, N) + np.random.randn(N) * 0.2  # theta
        r = a * np.sin(4 * t) + np.random.randn(N) * 0.2  # radius
        X[ix] = np.c_[r * np.sin(t), r * np.cos(t)]    # 按行连接俩个矩阵
        Y[ix] = j

    X = X.T
    Y = Y.T

    return X, Y





def layer_size(X, Y):
    n_x = X.shape[0]
    n_h = 4
    n_y = Y.shape[0]
    return (n_x, n_h, n_y)


def initialize_parameters(n_x, n_h, n_y):
    np.random.seed(2)
    W1 = np.random.randn(n_h, n_x)
    b1 = np.zeros((n_h, 1))
    W2 = np.random.randn(n_y, n_h)
    b2 = np.zeros((n_y, 1))
    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters



def forward_propagation(X, parameters):
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    Z1 = np.dot(W1, X) + b1
    A1 = np.tanh(Z1)
    Z2 = np.dot(W2, A1) + b2
    A2 = sigmoid(Z2)

    assert (A2.shape == (1, X.shape[1]))

    cache = {"Z1": Z1,
             "A1": A1,
             "Z2": Z2,
             "A2": A2}

    return A2, cache


def compute_cost(A2, Y, parameters):
    m = Y.shape[1]
    logprobs = np.multiply(np.log(A2), Y) + np.multiply(np.log(1-A2), (1-Y))
    cost = (-1.0 / m) * np.sum(logprobs)
    cost = np.squeeze(cost)
    return cost


def backward_propagation(parameters, cache, X, Y):
    m = X.shape[1]
    W1 = parameters["W1"]
    W2 = parameters["W2"]
    A1 = cache["A1"]
    A2 = cache["A2"]
    dZ2 = A2 - Y
    dW2 = (1.0 / m) * np.dot(dZ2, A1.T)
    db2 = (1.0 / m) * np.sum(dZ2, axis=1, keepdims=True)
    dZ1 = np.dot(W2.T, dZ2) * (1 - np.power(A1, 2))
    dW1 = 1.0 / m * np.dot(dZ1, X.T)
    db1 = 1.0 / m * np.sum(dZ1, axis=1, keepdims=True)
    grads = {"dW1": dW1,
             "db1": db1,
             "dW2": dW2,
             "db2": db2}

    return grads

def update_parameters(parameters, grads, learning_rate=1.2):
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    dW1 = grads["dW1"]
    db1 = grads["db1"]
    dW2 = grads["dW2"]
    db2 = grads["db2"]

    W1-= learning_rate * dW1
    b1 -= learning_rate * db1
    W2 -= learning_rate * dW2
    b2 -= learning_rate * db2

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

    return parameters

def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False):
    np.random.seed(3)
    n_x = layer_size(X, Y)[0]
    n_y = layer_size(X, Y)[2]

    parameters = initialize_parameters(n_x, n_h, n_y)
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    for i in range(num_iterations):
        A2, cache = forward_propagation(X, parameters)
        cost = compute_cost(A2, Y, parameters)
        grads = backward_propagation(parameters, cache, X, Y)
        parameters = update_parameters(parameters, grads, learning_rate=1.2)
        if print_cost and i % 100 == 0:
            print("Cost after iteration %i:%f"%(i, cost))
    return parameters


def predict(parameters, X):
    A2, cache = forward_propagation(X, parameters)
    predictions = (A2 > 0.5)
    return predictions


if __name__ == '__main__':
    X, Y = load_planar_dataset()
    plt.scatter(X[0, :], X[1, :], c=np.squeeze(Y), s=40, cmap=plt.cm.Spectral)
    parameters = nn_model(X, Y, n_h=4, num_iterations=10000, print_cost=True)

    # Plot the decision boundary
    plot_decision_boundary(lambda x: predict(parameters, x.T), X, np.squeeze(Y))
    plt.title("Decision Boundary for hidden layer size " + str(4))
    plt.show()

• 微调隐藏层

plt.figure(figsize=(16, 32))
hidden_layer_sizes = [1,2,3,4,5,20,50]
for i, n_h in enumerate(hidden_layer_sizes):
    plt.subplot(5, 2, i+1)
    plt.title("Hidden layer of size %d"%n_h)
    parameters = nn_model(X, Y, n_h, num_iterations=5000)
    plot_decision_boundary(lambda x: predict(parameters, x.T), X, np.squeeze(Y))
    predictions = predict(parameters, X)
    accuracy = float((np.dot(Y, predictions.T) + np.dot(1-Y, 1-predictions.T))/float(Y.size)*100)
    print("Accuracy for {} hidden units:{}%".format(n_h, accuracy))
plt.show()

Accuracy for 1 hidden units:61.5%
Accuracy for 2 hidden units:70.5%
Accuracy for 3 hidden units:66.25%
Accuracy for 4 hidden units:90.75%
Accuracy for 5 hidden units:91.0%
Accuracy for 20 hidden units:91.5%
Accuracy for 50 hidden units:90.75%