1、导入包
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
在jupyter上直接运行会出错，因为python没有提前下载好这些包。
提示错误：Could not find a version that satisfies the requirement matplotlib (from versions: )
解决：python3 -m pip install Image 注意一定要是python3尝试python出错，猜测是在python2.X里面没有这些包。
2、处理数据集
-一组标有是猫（=1）或者不是猫（=0）的m_train图片训练集
-一组标有是猫（=1）或者不是猫（=0）的m_test图片测试集
-每张图都是（num_px, num_px, 3）的正方形图
加载数据、确定数据大小：train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset() 其中train_set_x_orig，test_set_x_orig, 待预处理，表示一张图（plt.imshow(train_set_x_orig[index])）
train_set_x_orig (m_train, num_px, num_px, 3). （209，64，64，3）
train_set_y（1,m_train）(test同理)
重组图片表示 (num_px, num_px, 3)-> (num_px ∗ num_px ∗ 3, 1)
方法：X(a,b,c,d)-> (b∗c∗d, a) X_flatten=X.reshape(X.shape[0],-1).T
train_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T （12288，209）
集中化和标准化数据：train_set_x = train_set_x_flatten/255.
3、学习算法的一般架构
-初始化模型参数
-通过最小化成本来了解模型的参数
-使用学习到的参数进行预测（在测试集上）
-分析结果并得出结论
4、构建神经网络主要步骤
-定义模型结构（例如输入要素的数量）
-初始化模型的参数
-循环：
计算当前的损失（正向传播）
计算当前梯度（反向传播）
更新参数（梯度下降）
辅助函数：
def sigmoid(z):
s = 1 / (1 + np.exp(-z))
return s
初始化参数：
def initialize_with_zeros(dim):
w = np.zeros((dim, 1))
b = 0
assert(w.shape == (dim, 1))
assert(isinstance(b, float) or isinstance(b, int))
return w, b
dim = 2
w, b = initialize_with_zeros(dim)
初始化结果：** w ** [[ 0.] [ 0.]] ** b ** 0
正面传播和反向传播
def propagate(w, b, X, Y):
//w(num_px * num_px * 3, 1)
//X(num_px * num_px * 3, number of examples)
//Y(1,number of examples)
m = X.shape[1]
//正向传播
A = sigmoid(np.dot(w.T, X) + b) # compute activation
cost = -1 / m * np.sum(Y * np.log(A) + (1 - Y) * np.log(1 - A))
//反向传播
dw = 1 / m * np.dot(X, (A - Y).T)
db = 1 / m * np.sum(A - Y)
assert(dw.shape == w.shape)
assert(db.dtype == float)
cost = np.squeeze(cost)
assert(cost.shape == ())grads = {"dw": dw,
"db": db}
return grads, cost
w, b, X, Y = np.array([[1],[2]]), 2, np.array([[1,2],[3,4]]), np.array([[1,0]])
grads, cost = propagate(w, b, X, Y)
print ("dw = " + str(grads["dw"]))
print ("db = " + str(grads["db"]))
print ("cost = " + str(cost))
优化：𝜃=𝜃−𝛼 𝑑𝜃
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost = True):
costs = []
for i in range(num_iterations):
grads, cost = propagate(w, b, X, Y)
dw = grads["dw"]
db = grads["db"]
w = w - learning_rate * dw
b = b - learning_rate * db
if i % 100 == 0:
costs.append(cost)
if 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
预测：计算𝑌̂=𝐴=𝜎(𝑤𝑇𝑋+𝑏) 如果>0.5那么预测为1，<0.5预测为0
def predict(w, b, X):
m = X.shape[1]
Y_prediction = np.zeros((1,m))
w = w.reshape(X.shape[0], 1)
A = sigmoid(np.dot(w.T, X) + b)
for i in range(A.shape[1]):
if A[0, i] <= 0.5:
Y_prediction[0, i] = 0
else:
Y_prediction[0, i] = 1
assert(Y_prediction.shape == (1, m))
return Y_prediction
5、整合
def model(X_train, Y_train, X_test, Y_test, num_iterations = 2000, learning_rate = 0.5, print_cost = False):
w, b = initialize_with_zeros(X_train.shape[0])
parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
w = parameters["w"]
b = parameters["b"]
Y_prediction_test = predict(w, b, X_test)
Y_prediction_train = predict(w, b, X_train)
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
6、画折线图
# Plot learning curve (with costs)
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()
7、从自己的电脑里读取测试集图片
Click on "File" in the upper bar of this notebook, then click "Open" to go on your Coursera Hub.
Add your image to this Jupyter Notebook's directory, in the "images" folder
Change your image's name in the following code
Run the code and check if the algorithm is right (1 = cat, 0 = non-cat)!
代码：
my_image = "cat_in_iran.jpg"
fname = "images/" + my_image
image = np.array(ndimage.imread(fname, flatten=False))
my_image = scipy.misc.imresize(image, size=(num_px,num_px)).reshape((1, num_px*num_px*3)).T
my_predicted_image = predict(d["w"], d["b"], my_image)
plt.imshow(image)
print("y = " + str(np.squeeze(my_predicted_image)) + ", your algorithm predicts a \"" + classes[int(np.squeeze(my_predicted_image)),].decode("utf-8") + "\" picture.")
