【吴恩达深度学习L2W2】优化算法

主要内容：

1.批量梯度下降、随机梯度下降、小批量梯度下降

2.指数加权平均及修正（3中优化算法的基础）

3.动量梯度下降、RMSprop、Adam以及学习率衰减

4.局部最优解问题

主要案例：

构建三层神经网络，使用小批量梯度下降、带冲量的小批量梯度下降、带Adam的小批量梯度下降三种优化算法运行此神经网络，体会不同。

全部代码：

1.预备的模块

 opt_utils

import numpy as np
import matplotlib.pyplot as plt
import pylab
import scipy.io
import sklearn
import sklearn.datasets


def sigmoid(x):
    """
    Compute the sigmoid of x

    Arguments:
    x -- A scalar or numpy array of any size.

    Return:
    s -- sigmoid(x)
    """
    s = 1 / (1 + np.exp(-x))
    return s


def relu(x):
    """
    Compute the relu of x

    Arguments:
    x -- A scalar or numpy array of any size.

    Return:
    s -- relu(x)
    """
    s = np.maximum(0, x)

    return s


def load_params_and_grads(seed=1):
    np.random.seed(seed)
    W1 = np.random.randn(2, 3)
    b1 = np.random.randn(2, 1)
    W2 = np.random.randn(3, 3)
    b2 = np.random.randn(3, 1)

    dW1 = np.random.randn(2, 3)
    db1 = np.random.randn(2, 1)
    dW2 = np.random.randn(3, 3)
    db2 = np.random.randn(3, 1)

    return W1, b1, W2, b2, dW1, db1, dW2, db2


def initialize_parameters(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":
                    W1 -- weight matrix of shape (layer_dims[l], layer_dims[l-1])
                    b1 -- bias vector of shape (layer_dims[l], 1)
                    Wl -- weight matrix of shape (layer_dims[l-1], layer_dims[l])
                    bl -- bias vector of shape (1, layer_dims[l])

    Tips:
    - For example: the layer_dims for the "Planar Data classification model" would have been [2,2,1].
    This means W1's shape was (2,2), b1 was (1,2), W2 was (2,1) and b2 was (1,1). Now you have to generalize it!
    - In the for loop, use parameters['W' + str(l)] to access Wl, where l is the iterative integer.
    """

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

    for l in range(1, L):
        parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l - 1]) * np.sqrt(2 / layer_dims[l - 1])
        parameters['b' + str(l)] = np.zeros((layer_dims[l], 1))

        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


def compute_cost(a3, Y):
    """
    Implement the cost function

    Arguments:
    a3 -- post-activation, output of forward propagation
    Y -- "true" labels vector, same shape as a3

    Returns:
    cost - value of the cost function
    """
    m = Y.shape[1]

    logprobs = np.multiply(-np.log(a3), Y) + np.multiply(-np.log(1 - a3), 1 - Y)
    cost = 1. / m * np.sum(logprobs)

    return cost


def forward_propagation(X, parameters):
    """
    Implements the forward propagation (and computes the loss) presented in Figure 2.

    Arguments:
    X -- input dataset, of shape (input size, number of examples)
    parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
                    W1 -- weight matrix of shape ()
                    b1 -- bias vector of shape ()
                    W2 -- weight matrix of shape ()
                    b2 -- bias vector of shape ()
                    W3 -- weight matrix of shape ()
                    b3 -- bias vector of shape ()

    Returns:
    loss -- the loss function (vanilla logistic loss)
    """

    # retrieve parameters
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    W3 = parameters["W3"]
    b3 = parameters["b3"]

    # LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID
    z1 = np.dot(W1, X) + b1
    a1 = relu(z1)
    z2 = np.dot(W2, a1) + b2
    a2 = relu(z2)
    z3 = np.dot(W3, a2) + b3
    a3 = sigmoid(z3)

    cache = (z1, a1, W1, b1, z2, a2, W2, b2, z3, a3, W3, b3)

    return a3, cache


def backward_propagation(X, Y, cache):
    """
    Implement the backward propagation presented in figure 2.

    Arguments:
    X -- input dataset, of shape (input size, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat)
    cache -- cache output from forward_propagation()

    Returns:
    gradients -- A dictionary with the gradients with respect to each parameter, activation and pre-activation variables
    """
    m = X.shape[1]
    (z1, a1, W1, b1, z2, a2, W2, b2, z3, a3, W3, b3) = cache

    dz3 = 1. / m * (a3 - Y)
    dW3 = np.dot(dz3, a2.T)
    db3 = np.sum(dz3, axis=1, keepdims=True)

    da2 = np.dot(W3.T, dz3)
    dz2 = np.multiply(da2, np.int64(a2 > 0))
    dW2 = np.dot(dz2, a1.T)
    db2 = np.sum(dz2, axis=1, keepdims=True)

    da1 = np.dot(W2.T, dz2)
    dz1 = np.multiply(da1, np.int64(a1 > 0))
    dW1 = np.dot(dz1, X.T)
    db1 = np.sum(dz1, axis=1, keepdims=True)

    gradients = {"dz3": dz3, "dW3": dW3, "db3": db3,
                 "da2": da2, "dz2": dz2, "dW2": dW2, "db2": db2,
                 "da1": da1, "dz1": dz1, "dW1": dW1, "db1": db1}

    return gradients


def predict(X, y, parameters):
    """
    This function is used to predict the results of a  n-layer neural network.

    Arguments:
    X -- data set of examples you would like to label
    parameters -- parameters of the trained model

    Returns:
    p -- predictions for the given dataset X
    """

    m = X.shape[1]
    p = np.zeros((1, m), dtype=np.int32)

    # Forward propagation
    a3, caches = forward_propagation(X, parameters)

    # convert probas to 0/1 predictions
    for i in range(0, a3.shape[1]):
        if a3[0, i] > 0.5:
            p[0, i] = 1
        else:
            p[0, i] = 0

    # print results

    # print ("predictions: " + str(p[0,:]))
    # print ("true labels: " + str(y[0,:]))
    print("Accuracy: " + str(np.mean((p[0, :] == y[0, :]))))

    return p


def load_2D_dataset():
    data = scipy.io.loadmat('datasets/data.mat')
    train_X = data['X'].T
    train_Y = data['y'].T
    test_X = data['Xval'].T
    test_Y = data['yval'].T

    plt.scatter(train_X[0, :], train_X[1, :], c=train_Y, s=40, cmap=plt.cm.Spectral);

    return train_X, train_Y, test_X, test_Y


def plot_decision_boundary(model, X, y):
    # Set min and max values and give it some padding
    x_min, x_max = X[0, :].min() - 1, X[0, :].max() + 1
    y_min, y_max = X[1, :].min() - 1, X[1, :].max() + 1
    h = 0.01
    # Generate a grid of points with distance h between them
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
    # Predict the function value for the whole grid
    Z = model(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    # Plot the contour and training examples
    plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)
    plt.ylabel('x2')
    plt.xlabel('x1')
    plt.scatter(X[0, :], X[1, :], c=y, cmap=plt.cm.Spectral)
    plt.show()


def predict_dec(parameters, X):
    """
    Used for plotting decision boundary.

    Arguments:
    parameters -- python dictionary containing your parameters
    X -- input data of size (m, K)

    Returns
    predictions -- vector of predictions of our model (red: 0 / blue: 1)
    """

    # Predict using forward propagation and a classification threshold of 0.5
    a3, cache = forward_propagation(X, parameters)
    predictions = (a3 > 0.5)
    return predictions


def load_dataset():
    np.random.seed(3)
    train_X, train_Y = sklearn.datasets.make_moons(n_samples=300, noise=.2)  # 300 #0.2
    # Visualize the data
    plt.scatter(train_X[:, 0], train_X[:, 1], c=train_Y, s=40, cmap=plt.cm.Spectral);
    pylab.show()
    train_X = train_X.T
    train_Y = train_Y.reshape((1, train_Y.shape[0]))

    return train_X, train_Y

2.三种不同的优化算法

import numpy as np
import matplotlib.pyplot as plt
import pylab
import math
from opt_utils import load_params_and_grads, initialize_parameters, forward_propagation, backward_propagation
from opt_utils import compute_cost, predict, predict_dec, plot_decision_boundary, load_dataset


# 从（X，Y）中创建一个随机的mini-batch列表
# shuffle+partition
def random_mini_batches(X, Y, mini_batch_size=64, seed=0):
    np.random.seed(seed)
    # 训练样本数量
    m = X.shape[1]
    mini_batches = []
    # Shuffle (X, Y)
    # 随机生成一个排列
    permutation = list(np.random.permutation(m))
    shuffled_X = X[:, permutation]
    shuffled_Y = Y[:, permutation].reshape((1, m))
    # Partition (shuffled_X, shuffled_Y) 此处不包含最后一组
    # 有多少完整的 minibatches
    num_complete_minibatches = math.floor(m / mini_batch_size)
    # 划分完整的 mini-batch
    for k in range(0, num_complete_minibatches):
        mini_batch_X = shuffled_X[:, k * mini_batch_size: (k + 1) * mini_batch_size]
        mini_batch_Y = shuffled_Y[:, k * mini_batch_size: (k + 1) * mini_batch_size]
        # 将划分好的minni_batch_X和mini_batch_y放入mini_batches中
        mini_batch = (mini_batch_X, mini_batch_Y)
        mini_batches.append(mini_batch)
    # 如果训练集的大小刚好是mini_batch_size的整数倍，那么这里已经处理完了
    # 如果训练集的大小不是mini_batch_size的整数倍，那么最后肯定会剩下一些，我们要把它处理了
    if m % mini_batch_size != 0:  # 还有剩下的部分
        # 获取最后剩余的部分
        mini_batch_X = shuffled_X[:, num_complete_minibatches * mini_batch_size: m]
        mini_batch_Y = shuffled_Y[:, num_complete_minibatches * mini_batch_size: m]
        mini_batch = (mini_batch_X, mini_batch_Y)
        mini_batches.append(mini_batch)

    return mini_batches


# 梯度下降更新参数
def update_parameters_with_gd(parameters, grads, learning_rate):
    L = len(parameters) // 2  # number of layers in the neural networks
    # Update rule for each parameter
    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

# 动量梯度下降初始化速度
def initialize_velocity(parameters):
    """
    参数：
        parameters - 一个字典，包含了以下参数：
            parameters["W" + str(l)] = Wl
            parameters["b" + str(l)] = bl
    """
    L = len(parameters) // 2  # number of layers in the neural networks
    v = {}
    # 初始化速度为0  dW=0 db=0
    for l in range(L):
        v["dW" + str(l + 1)] = np.zeros(parameters['W' + str(l + 1)].shape)
        v["db" + str(l + 1)] = np.zeros(parameters['b' + str(l + 1)].shape)
    return v

# 动量梯度下降更新参数
def update_parameters_with_momentum(parameters, grads, v, beta, learning_rate):
    L = len(parameters) // 2
    for l in range(L):
        # 计算速度
        v["dW" + str(l + 1)] = beta * v["dW" + str(l + 1)] + (1 - beta) * grads['dW' + str(l + 1)]
        v["db" + str(l + 1)] = beta * v["db" + str(l + 1)] + (1 - beta) * grads['db' + str(l + 1)]
        # 更新参数
        parameters["W" + str(l + 1)] = parameters['W' + str(l + 1)] - learning_rate * v["dW" + str(l + 1)]
        parameters["b" + str(l + 1)] = parameters['b' + str(l + 1)] - learning_rate * v["db" + str(l + 1)]
    return parameters, v

# Adam初始化
def initialize_adam(parameters):
    L = len(parameters) // 2
    v = {}
    s = {}
    for l in range(L):
        ### START CODE HERE ### (approx. 4 lines)
        v["dW" + str(l + 1)] = np.zeros(parameters["W" + str(l + 1)].shape)
        v["db" + str(l + 1)] = np.zeros(parameters["b" + str(l + 1)].shape)
        s["dW" + str(l + 1)] = np.zeros(parameters["W" + str(l + 1)].shape)
        s["db" + str(l + 1)] = np.zeros(parameters["b" + str(l + 1)].shape)
        ### END CODE HERE ###

    return v, s

# Adam更新参数
def update_parameters_with_adam(parameters, grads, v, s, t, learning_rate=0.01,
                                beta1=0.9, beta2=0.999, epsilon=1e-8):

    L = len(parameters) // 2
    v_corrected = {}
    s_corrected = {}
    # Perform Adam update on all parameters
    for l in range(L):
        v["dW" + str(l + 1)] = beta1 * v["dW" + str(l + 1)] + (1 - beta1) * grads['dW' + str(l + 1)]
        v["db" + str(l + 1)] = beta1 * v["db" + str(l + 1)] + (1 - beta1) * grads['db' + str(l + 1)]

        v_corrected["dW" + str(l + 1)] = v["dW" + str(l + 1)] / (1 - (beta1) ** t)
        v_corrected["db" + str(l + 1)] = v["db" + str(l + 1)] / (1 - (beta1) ** t)

        s["dW" + str(l + 1)] = beta2 * s["dW" + str(l + 1)] + (1 - beta2) * (grads['dW' + str(l + 1)] ** 2)
        s["db" + str(l + 1)] = beta2 * s["db" + str(l + 1)] + (1 - beta2) * (grads['db' + str(l + 1)] ** 2)

        s_corrected["dW" + str(l + 1)] = s["dW" + str(l + 1)] / (1 - (beta2) ** t)
        s_corrected["db" + str(l + 1)] = s["db" + str(l + 1)] / (1 - (beta2) ** t)

        # 更新参数
        parameters["W" + str(l + 1)] = parameters["W" + str(l + 1)] - learning_rate * (
                    v_corrected["dW" + str(l + 1)] / np.sqrt(s_corrected["dW" + str(l + 1)] + epsilon))
        parameters["b" + str(l + 1)] = parameters["b" + str(l + 1)] - learning_rate * (
                    v_corrected["db" + str(l + 1)] / np.sqrt(s_corrected["db" + str(l + 1)] + epsilon))
    return parameters, v, s

3.搭建模型进行训练

# 加载数据集
train_X, train_Y = load_dataset()
# 定义模型
def model(X, Y, layers_dims, optimizer, learning_rate=0.0007, mini_batch_size=64, beta=0.9,
          beta1=0.9, beta2=0.999, epsilon=1e-8, num_epochs=10000, print_cost=True):

    L = len(layers_dims)
    costs = []
    t = 0
    seed = 10
    # 初始化参数
    parameters = initialize_parameters(layers_dims)
    # 初始化优化器
    if optimizer == "gd":
        pass
    elif optimizer == "momentum":
        v = initialize_velocity(parameters)
    elif optimizer == "adam":
        v, s = initialize_adam(parameters)

    # 优化loop
    for i in range(num_epochs):
        seed = seed + 1
        # 每个epoch都打乱数据
        minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
        for minibatch in minibatches:
            (minibatch_X, minibatch_Y) = minibatch
            # 前向传播
            a3, caches = forward_propagation(minibatch_X, parameters)
            # 计算损失
            cost = compute_cost(a3, minibatch_Y)
            # 后向传播
            grads = backward_propagation(minibatch_X, minibatch_Y, caches)

            # 更新参数
            if optimizer == "gd":
                parameters = update_parameters_with_gd(parameters, grads, learning_rate)
            elif optimizer == "momentum":
                parameters, v = update_parameters_with_momentum(parameters, grads, v, beta, learning_rate)
            elif optimizer == "adam":
                t = t + 1  # t用来修正
                parameters, v, s = update_parameters_with_adam(parameters, grads, v, s,
                                                               t, learning_rate, beta1, beta2, epsilon)

        # 打印损失
        if print_cost and i % 1000 == 0:
            print("Cost after epoch %i: %f" % (i, cost))
        if print_cost and i % 100 == 0:
            costs.append(cost)

    # plot the cost
    plt.plot(costs)
    plt.ylabel('cost')
    plt.xlabel('epochs (pear 100)')
    plt.title("Learning rate = " + str(learning_rate))
    plt.show()
    pylab.show()

    return parameters


# 小批量梯度下降
# train 3-layer model
layers_dims = [train_X.shape[0], 5, 2, 1]
parameters = model(train_X, train_Y, layers_dims, optimizer = "gd")
# Predict
predictions = predict(train_X, train_Y, parameters)
# Plot decision boundary
plt.title("Model with Gradient Descent optimization")
axes = plt.gca()
axes.set_xlim([-1.5,2.5])
axes.set_ylim([-1,1.5])
plot_decision_boundary(lambda x: predict_dec(parameters, x.T), train_X, train_Y)


# 带动量的小批量梯度下降
# train 3-layer model
layers_dims = [train_X.shape[0], 5, 2, 1]
parameters = model(train_X, train_Y, layers_dims, beta = 0.9, optimizer = "momentum")
# Predict
predictions = predict(train_X, train_Y, parameters)
# Plot decision boundary
plt.title("Model with Momentum optimization")
axes = plt.gca()
axes.set_xlim([-1.5,2.5])
axes.set_ylim([-1,1.5])
plot_decision_boundary(lambda x: predict_dec(parameters, x.T), train_X, train_Y)

# 带Adam的小批量梯度下降
# train 3-layer model
layers_dims = [train_X.shape[0], 5, 2, 1]
parameters = model(train_X, train_Y, layers_dims, optimizer = "adam")
# Predict
predictions = predict(train_X, train_Y, parameters)
# Plot decision boundary
plt.title("Model with Adam optimization")
axes = plt.gca()
axes.set_xlim([-1.5,2.5])
axes.set_ylim([-1,1.5])
plot_decision_boundary(lambda x: predict_dec(parameters, x.T), train_X, train_Y)

结果分析：

1.冲量通常会有所帮助，但是鉴于学习率低和数据集过于简单，其影响几乎可以忽略不计。

2.Adam明显胜过小批次梯度下降和冲量。如果在此简单数据集上运行更多epoch，则这三种方法都将产生非常好的结果。但是，Adam收敛得更快。

3.Adam的优势包括：相对较低的内存要求（尽管高于梯度下降和带冲量的梯度下降）；

    即使很少调整超参数，通常也能很好地工作（𝛼除外）。