吴恩达深度学习公开课第二周编程练习2

关注公众号【算法码上来】，每日算法干货马上就来！

这次练习是实现logistic回归模型的神经网络，来预测一张图片是不是一只猫。
我把代码整合在了一起，如下：

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

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]

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

dim = 2
w, b = initialize_with_zeros(dim)

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

def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost = False):
    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

params, grads, costs = optimize(w, b, X, Y, num_iterations= 100, learning_rate = 0.009, print_cost = False)

def predict(w, b, X):

    m = X.shape[1]
    Y_prediction = np.zeros((1,m))
    w = w.reshape(X.shape[0], 1)
    A = sigmoid(w.T.dot(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

但是这样看起来太乱太复杂了，于是最后一个练习将训练过程合并成了一个model，代码如下：

def model(X_train, Y_train, X_test, Y_test, num_iterations = 2000, learning_rate = 0.5, print_cost = False):
    w, b = np.zeros((X_train.shape[0], 1)), 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)
    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)