复习-猫咪识别-逻辑回归

嗯…今天的话就是把内容复习了一下 按照自己的理解推了一下向量化的内容 还有就是测试了一下不同初始化方式 对模型预测结果的影响 就是自己随便测试的(´･_･`)

学习率都是0.005没变
图一是迭代次数2000 初始化方式：置0
图二是迭代次数20000 初始化方式：置0
图三到五是迭代次数20000 初始化方式：随机

                       

图1-2

     

图3-5

实验次数不是很多，但对于初始化随机的情况，保证每次迭代次数相同的情况下，每次的结果可能会有所不同；然后置0的情况就每次结果都一样，改变迭代次数时才影响结果。

emmmmm 反正感觉我今天就是推了一下公式 复习了一下 然后简单实验一下 结果都不一定对来着 但学的开心的 就这样⁄(⁄ ⁄ ⁄ω⁄ ⁄ ⁄)⁄

附上：

cat.py

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

def initializing(dim,flag=0):
    if(flag==0):
        w=np.zeros((dim,1))
    else:
        w=np.random.rand(dim,1)
    b=0.

    assert(w.shape==(dim,1))
    assert (isinstance(b, float) or isinstance(b, int))
    return w,b

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

def propagate(X,Y,w,b):
    m = X.shape[1]
    #forward
    Z=np.dot(w.T,X)+b
    A=sigmoid(Z)
    cost = -np.sum(Y * np.log(A) + (1 - Y) * np.log(1 - A)) / m

    #backforward:
    dZ=A-Y
    dw=np.dot(X,dZ.T)/m
    db=np.sum(dZ)/m

    assert (dw.shape == w.shape)
    assert (db.dtype == float)
    cost = np.squeeze(cost)
    assert (cost.shape == ())

    grade={"dw":dw,"db":db}

    return grade,cost

def optimize(X,Y,w,b,num_it,learning_it,print_cost=False):
    costs=[]
    a=learning_it
    for i in range(num_it):
        grade,cost=propagate(X,Y,w,b)

        dw=grade["dw"]
        db=grade["db"]

        w=w-a*dw
        b=b-a*db

        #每迭代一百次，输出一次，loss
        if i % 100==0:
            costs.append(cost)
            if(print_cost==True):
                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))#构建输出矩阵
    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] = 1
        else:
            Y_prediction[0, i] = 0

    assert (Y_prediction.shape == (1, m))

    return Y_prediction

def model(X_Train,Y_Train,X_Test,Y_Test,num_it,learning_it,print_cost=False):

    w,b=initializing(X_Train.shape[0],1)

    params, grads, costs=optimize(X_Train,Y_Train,w,b,num_it,learning_it,print_cost)
    #获得优化后的参数
    w = params["w"]
    b = params["b"]

    Y_prediction_test = predict(w, b, X_Test)
    Y_prediction_train = predict(w, b, X_Train)

    #给出测试和训练的结果
    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_it,
         "num_iterations": num_it}
    return d

def curve_costs(costs,learning_it):
    costs=np.squeeze(costs)
    plt.plot(costs)
    plt.ylabel('cost')
    plt.xlabel('iterations (per hundreds)')
    plt.title("Learning rate =" + str(learning_it))
    plt.show()

if __name__=="__main__":
    #测试给定数据集
    # 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[2]

    # 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.

    d=model(train_set_x, train_set_y, test_set_x, test_set_y, num_it =2500,learning_it = 0.005, print_cost = True)
    #画出数据的cost曲线：
    curve_costs(d["costs"],d["learning_rate"])



    #测试图片
    my_image = "my_image2.jpg"  # change this to the name of your image file
    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.")

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

参考：

吴恩达学习课程