cs230 深度学习 Lecture 2 编程作业： Logistic Regression with a Neural Network mindset

本文结构：

将 Logistic 表达为神经网络的形式
构建模型
1. 导入包
2. 获得数据
3. 并进行预处理：格式转换，归一化
4. 整合模型：
  - A. 构建模型
    - a. 初始化参数：w 和 b 为 0
    - b. 前向传播：计算当前的损失
    - c. 反向更新：计算当前的梯度
  - B. 梯度更新求模型参数
  - C. 进行预测
5. 绘制学习曲线

1. 将 Logistic 表达为神经网络的形式

本文的目的是要用神经网络的思想实现 Logistic Regression，输入一张图片就可以判断该图片是不是猫。

那么什么是神经网络呢？
可以看我之前写的这篇文章：

什么是神经网络

其中一个很重要的概念，神经元：

再来看 Logistic 模型的表达：

那么把 Logistic 表达为神经网络的形式为：

（关于 Logistic 可以看这两篇文章：
Logistic Regression 为什么用极大似然函数
Logistic regression 为什么用 sigmoid ？）

接下来就可以构建模型:

2. 构建模型

我们的目的是学习 www 和 b" role="presentation" style="position: relative;">bbb 使 cost function JJJ 达到最小，

方法就是：

通过前向传播 (forward propagation) 计算当前的损失，
通过反向传播 (backward propagation) 计算当前的梯度，
再用梯度下降法对参数进行优化更新 (gradient descent)

关于反向传播可以看这两篇文章：
手写，纯享版反向传播算法公式推导

构建模型，训练模型，并进行预测，包含下面几步：

导入包
获得数据
并进行预处理：格式转换，归一化
整合模型：
- A. 构建模型
  - a. 初始化参数：w 和 b 为 0
  - b. 前向传播：计算当前的损失
  - c. 反向更新：计算当前的梯度
- B. 梯度更新求模型参数
- C. 进行预测
绘制学习曲线

下面进入详细代码：

1. 导入包

引入需要的 packages，
其中，
h5py 是 python 中用于处理 H5 文件的接口，
PIL 和 scipy 在本文是用自己的图片来测试训练好的模型，
load_dataset 读取数据

import numpy as np
import matplotlib.pyplot as plt
import h5py
import scipy
from PIL import Image
from scipy import ndimage
from lr_utils import load_dataset%matplotlib inline

其中 lr_utils.py 如下，是对 H5 文件进行解析：

#lr_utils.py  import numpy as np
import h5py  def load_dataset():  train_dataset = h5py.File('datasets/train_catvnoncat.h5', "r")  train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features  train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels  test_dataset = h5py.File('datasets/test_catvnoncat.h5', "r")  test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features  test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels  classes = np.array(test_dataset["list_classes"][:]) # the list of classes  train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))  test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))  return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes

2. 获得数据

# Loading the data (cat/non-cat)
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()

可以看一下图片的例子：

# Example of a picture
index = 25
plt.imshow(train_set_x_orig[index])
print ("y = " + str(train_set_y[:,index]) + ", it's a '" + classes[np.squeeze(train_set_y[:,index])].decode("utf-8") +  "' picture.")

3. 进行预处理：格式转换，归一化

这时需要获得下面几个值：

m_train (训练样本数量)
m_test (测试样本数量)
num_px (训练数据集的长和宽)

### START CODE HERE ### (≈ 3 lines of code)### STA
m_train = train_set_y.shape[1]
m_test = test_set_y.shape[1]
num_px = train_set_x_orig.shape[1]
### END CODE HERE ###print ("Number of training examples: m_train = " + str(m_train))
print ("Number of testing examples: m_test = " + str(m_test))
print ("Height/Width of each image: num_px = " + str(num_px))
print ("Each image is of size: (" + str(num_px) + ", " + str(num_px) + ", 3)")
print ("train_set_x shape: " + str(train_set_x_orig.shape))
print ("train_set_y shape: " + str(train_set_y.shape))
print ("test_set_x shape: " + str(test_set_x_orig.shape))
print ("test_set_y shape: " + str(test_set_y.shape))

图像需要进行 reshape，原本是 (num_px, num_px, 3)，要扁平化为一个向量 (num_px * num_px * 3, 1)，
将 (a, b, c, d) 维的矩阵转换为 (b∗c∗d, a) 可以用： X_flatten = X.reshape(X.shape[0], -1).T

# Reshape the training and test examples### START CODE HERE ### (≈ 2 lines of code)
train_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T
test_set_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T
### END CODE HERE ###print ("train_set_x_flatten shape: " + str(train_set_x_flatten.shape))
print ("train_set_y shape: " + str(train_set_y.shape))
print ("test_set_x_flatten shape: " + str(test_set_x_flatten.shape))
print ("test_set_y shape: " + str(test_set_y.shape))
print ("sanity check after reshaping: " + str(train_set_x_flatten[0:5,0]))

预处理还常常包括对数据进行中心化和标准化，图像数据的话，可以简单除以最大的像素值：

train_set_x = train_set_x_flatten / 255.
test_set_x = test_set_x_flatten / 255.

4. 整合模型

- A. 构建模型- a. 初始化参数：w 和 b 为 0- b. 前向传播：计算当前的损失- c. 反向更新：计算当前的梯度
- B. 梯度更新求模型参数
- C. 进行预测

先来 A. 构建模型

按照前面提到的三步：
初始化参数：w 和 b 为 0
前向传播：计算当前的损失
反向更新：计算当前的梯度

首先需要一个辅助函数 sigmoid( w^T x + b)

# GRADED FUNCTION: sigmoiddef sigmoid(z):"""Compute the sigmoid of zArguments:x -- A scalar or numpy array of any size.Return:s -- sigmoid(z)"""### START CODE HERE ### (≈ 1 line of code)s = 1 / (1 + np.exp(-z))### END CODE HERE ###return s

a. 初始化参数：w 和 b 为 0

# GRADED FUNCTION: initialize_with_zerosdef initialize_with_zeros(dim):"""This function creates a vector of zeros of shape (dim, 1) for w and initializes b to 0.Argument:dim -- size of the w vector we want (or number of parameters in this case)Returns:w -- initialized vector of shape (dim, 1)b -- initialized scalar (corresponds to the bias)"""### START CODE HERE ### (≈ 1 line of code)w = np.zeros(shape=(dim, 1))b = 0### END CODE HERE ###assert(w.shape == (dim, 1))assert(isinstance(b, float) or isinstance(b, int))return w, b

b. 前向传播：计算当前的损失
c. 反向更新：计算当前的梯度

# GRADED FUNCTION: propagatedef propagate(w, b, X, Y):"""Implement the cost function and its gradient for the propagation explained aboveArguments:w -- weights, a numpy array of size (num_px * num_px * 3, 1)b -- bias, a scalarX -- data of size (num_px * num_px * 3, number of examples)Y -- true "label" vector (containing 0 if non-cat, 1 if cat) of size (1, number of examples)Return:cost -- negative log-likelihood cost for logistic regressiondw -- gradient of the loss with respect to w, thus same shape as wdb -- gradient of the loss with respect to b, thus same shape as bTips:- Write your code step by step for the propagation"""m = X.shape[1]# FORWARD PROPAGATION (FROM X TO COST)### START CODE HERE ### (≈ 2 lines of code)A = sigmoid(np.dot(w.T, X) + b)  # compute activationcost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A)))  # compute cost### END CODE HERE #### BACKWARD PROPAGATION (TO FIND GRAD)### START CODE HERE ### (≈ 2 lines of code)dw = (1 / m) * np.dot(X, (A - Y).T)db = (1 / m) * np.sum(A - Y)### END CODE HERE ###assert(dw.shape == w.shape)assert(db.dtype == float)cost = np.squeeze(cost)assert(cost.shape == ())grads = {"dw": dw,"db": db}return grads, cost

B. 梯度更新求模型参数

这一步 optimize 的目的是要学习 w" role="presentation" style="position: relative;">www 和 bbb 使 cost function J" role="presentation" style="position: relative;">JJJ 达到最小，
用到的方法是梯度下降 θ=θ−α dθθ=θ−αdθ \theta = \theta - \alpha \text{ } d\theta，

# GRADED FUNCTION: optimizedef optimize(w, b, X, Y, num_iterations, learning_rate, print_cost = False):"""This function optimizes w and b by running a gradient descent algorithmArguments:w -- weights, a numpy array of size (num_px * num_px * 3, 1)b -- bias, a scalarX -- data of shape (num_px * num_px * 3, number of examples)Y -- true "label" vector (containing 0 if non-cat, 1 if cat), of shape (1, number of examples)num_iterations -- number of iterations of the optimization looplearning_rate -- learning rate of the gradient descent update ruleprint_cost -- True to print the loss every 100 stepsReturns:params -- dictionary containing the weights w and bias bgrads -- dictionary containing the gradients of the weights and bias with respect to the cost functioncosts -- list of all the costs computed during the optimization, this will be used to plot the learning curve.Tips:You basically need to write down two steps and iterate through them:1) Calculate the cost and the gradient for the current parameters. Use propagate().2) Update the parameters using gradient descent rule for w and b."""costs = []for i in range(num_iterations):# Cost and gradient calculation (≈ 1-4 lines of code)### START CODE HERE ### grads, cost = propagate(w, b, X, Y)### END CODE HERE #### Retrieve derivatives from gradsdw = grads["dw"]db = grads["db"]# update rule (≈ 2 lines of code)### START CODE HERE ###w = w - learning_rate * dw  # need to broadcastb = b - learning_rate * db### END CODE HERE #### Record the costsif i % 100 == 0:costs.append(cost)# Print the cost every 100 training examplesif print_cost and i % 100 == 0:print ("Cost after iteration %i: %f" % (i, cost))params = {"w": w,"b": b}grads = {"dw": dw,"db": db}return params, grads, costs

C. 进行预测

# GRADED FUNCTION: predictdef predict(w, b, X):'''Predict whether the label is 0 or 1 using learned logistic regression parameters (w, b)Arguments:w -- weights, a numpy array of size (num_px * num_px * 3, 1)b -- bias, a scalarX -- data of size (num_px * num_px * 3, number of examples)Returns:Y_prediction -- a numpy array (vector) containing all predictions (0/1) for the examples in X'''m = X.shape[1]Y_prediction = np.zeros((1, m))w = w.reshape(X.shape[0], 1)# Compute vector "A" predicting the probabilities of a cat being present in the picture### START CODE HERE ### (≈ 1 line of code)A = sigmoid(np.dot(w.T, X) + b)### END CODE HERE ###for i in range(A.shape[1]):# Convert probabilities a[0,i] to actual predictions p[0,i]### START CODE HERE ### (≈ 4 lines of code)Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0### END CODE HERE ###assert(Y_prediction.shape == (1, m))return Y_prediction

下面为整合的逻辑回归模型：

将参数初始化，优化求参，预测整合在一起，

输入为训练集，测试集，迭代次数，学习速率，是否打印中间损失
打印 test 和 train 集的预测准确率
返回的 d 含有参数 w，b，还有 test train 集上面的预测值，

# GRADED FUNCTION: modeldef model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=0.5, print_cost=False):"""Builds the logistic regression model by calling the function you've implemented previouslyArguments:X_train -- training set represented by a numpy array of shape (num_px * num_px * 3, m_train)Y_train -- training labels represented by a numpy array (vector) of shape (1, m_train)X_test -- test set represented by a numpy array of shape (num_px * num_px * 3, m_test)Y_test -- test labels represented by a numpy array (vector) of shape (1, m_test)num_iterations -- hyperparameter representing the number of iterations to optimize the parameterslearning_rate -- hyperparameter representing the learning rate used in the update rule of optimize()print_cost -- Set to true to print the cost every 100 iterationsReturns:d -- dictionary containing information about the model."""### START CODE HERE #### initialize parameters with zeros (≈ 1 line of code)w, b = initialize_with_zeros(X_train.shape[0])# Gradient descent (≈ 1 line of code)parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)# Retrieve parameters w and b from dictionary "parameters"w = parameters["w"]b = parameters["b"]# Predict test/train set examples (≈ 2 lines of code)Y_prediction_test = predict(w, b, X_test)Y_prediction_train = predict(w, b, X_train)### END CODE HERE #### Print train/test Errorsprint("train accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100))print("test accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100))d = {"costs": costs,"Y_prediction_test": Y_prediction_test, "Y_prediction_train" : Y_prediction_train, "w" : w, "b" : b,"learning_rate" : learning_rate,"num_iterations": num_iterations}return d

下面代码进行模型训练：

d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)

结果：

Cost after iteration 0: 0.693147
Cost after iteration 100: 0.584508
Cost after iteration 200: 0.466949
Cost after iteration 300: 0.376007
Cost after iteration 400: 0.331463
Cost after iteration 500: 0.303273
Cost after iteration 600: 0.279880
Cost after iteration 700: 0.260042
Cost after iteration 800: 0.242941
Cost after iteration 900: 0.228004
Cost after iteration 1000: 0.214820
Cost after iteration 1100: 0.203078
Cost after iteration 1200: 0.192544
Cost after iteration 1300: 0.183033
Cost after iteration 1400: 0.174399
Cost after iteration 1500: 0.166521
Cost after iteration 1600: 0.159305
Cost after iteration 1700: 0.152667
Cost after iteration 1800: 0.146542
Cost after iteration 1900: 0.140872
train accuracy: 99.04306220095694 %
test accuracy: 70.0 %

得到模型后可以看指定 index 所代表图片的预测值：

# Example of a picture that was wrongly classified.# Exampl
index = 5
plt.imshow(test_set_x[:,index].reshape((num_px, num_px, 3)))
print ("y = " + str(test_set_y[0, index]) + ", you predicted that it is a \"" + classes[d["Y_prediction_test"][0, index]].decode("utf-8") +  "\" picture.")

5. 绘制学习曲线

# Plot learning curve (with costs)# Plot l
costs = np.squeeze(d['costs'])
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('iterations (per hundreds)')
plt.title("Learning rate =" + str(d["learning_rate"]))
plt.show()

可以看出 costs 是在下降的，如果增加迭代次数，那么训练数据的准确率会进一步提高，但是测试数据集的准确率可能会明显下降，这就是由于过拟合造成的。

还可以对比下不同学习率对应下的学习效果：

learning_rates = [0.01, 0.001, 0.0001]
models = {}
for i in learning_rates:print ("learning rate is: " + str(i))models[str(i)] = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 1500, learning_rate = i, print_cost = False)print ('\n' + "-------------------------------------------------------" + '\n')for i in learning_rates:plt.plot(np.squeeze(models[str(i)]["costs"]), label= str(models[str(i)]["learning_rate"]))plt.ylabel('cost')
plt.xlabel('iterations')legend = plt.legend(loc='upper center', shadow=True)
frame = legend.get_frame()
frame.set_facecolor('0.90')
plt.show()

当学习率过大 (例 0.01) 时，costs 出现上下震荡，甚至可能偏离，不过这里 0.01 最终幸运地收敛到了一个比较好的值。

推荐阅读
历史技术博文链接汇总
也许可以找到你想要的：
[入门问题][TensorFlow][深度学习][强化学习][神经网络][机器学习][自然语言处理][聊天机器人]