知识点汇总

作业内容：用logistic回归对猫进行分类

numpy知识点：

1. 查看矩阵维度： x.shape
   
2. 初始化0矩阵： np.zeros((dim1, dim2))
   
3. 去掉矩阵中大小是1的维度： x = np.squeeze(x)
4. 将(a, b, c, d)矩阵转换为(b\(*\)c\(*\)d, a)： X_flatten = X.reshape(X.shape[0], -1).T

算法逻辑梳理：

1. 导入包
2. 输入数据处理： 载入图片，格式转换，归一化
3. 初始化参数
4. 前向传播
5. 反向更新
6. 预测结果
7. 收敛曲线图

logistic回归代码：

# 整体代码

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

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

m_train = train_set_x_orig.shape[0]
m_test = test_set_x_orig.shape[0]
num_px = train_set_x_orig.shape[1]

# Reshape the training and test examples
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

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


def sigmoid(z):
    s = 1 / (1 + np.exp(-z))
    return s


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


def propagate(w, b, X, Y):
    m = X.shape[1]
    
    # FORWARD PROPAGATION (FROM X TO COST)
    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))         # compute cost
    
    # BACKWARD PROPAGATION (TO FIND GRAD)
    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


def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost = False):
    costs = []
    
    for i in range(num_iterations):      
        # Cost and gradient calculation 
        grads, cost = propagate(w, b, X, Y)
        
        # Retrieve derivatives from grads
        dw = grads["dw"]
        db = grads["db"]
        
        # update rule
        w = w - learning_rate * dw
        b = b - learning_rate * db
        
        # Record the costs
        if i % 100 == 0:
            costs.append(cost)
        
        # Print the cost every 100 training examples
        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


def predict(w, b, 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
    A = sigmoid(np.dot(w.T, X) + b)

    for i in range(A.shape[1]):  
        # Convert probabilities A[0,i] to actual predictions p[0,i]
        Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0
    
    assert(Y_prediction.shape == (1, m))
    
    return Y_prediction


def model(X_train, Y_train, X_test, Y_test, num_iterations = 2000, learning_rate = 0.5, print_cost = False):
    # initialize parameters with zeros
    w, b = initialize_with_zeros(X_train.shape[0])

    # Gradient descent 
    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
    Y_prediction_test = predict(w, b, X_test)
    Y_prediction_train = predict(w, b, X_train)

    # Print train/test Errors
    print("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


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

# 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