参考大佬的博客https://blog.csdn.net/u013733326/article/details/79639509
代码：
# coding=utf-8 # This is a sample Python script. # Press ⌃R to execute it or replace it with your code. # Press Double ⇧ to search everywhere for classes, files, tool windows, actions, and settings. import numpy as np import matplotlib.pyplot as plt import h5py from lr_utils import load_dataset # Press the green button in the gutter to run the script. 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 def sigmoid(z): return 1.0 / (1.0 + np.exp(-z)) def init(dim): w = np.zeros(shape=(dim, 1)) b = 0 assert (w.shape == (dim, 1)) assert (isinstance(b, int) or isinstance(b, float)) return w, b def propagate(w, b, X, Y): m = X.shape[1] A = sigmoid(np.dot(w.T, X) + b) # print("m1: ", m) cost = (-1.0 / m) * np.sum(Y * np.log(A) + (1.0 - Y) * (np.log((1.0 - A)))) dw = (1.0 / m) * np.dot(X, (A - Y).T) db = (1.0 / 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): costs = [] for i in range(num_iterations): # print("i: ", i) 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) # 记录成本 if i % 100 == 0: costs.append(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) A = sigmoid(np.dot(w.T, X) + b) for i in range(A.shape[1]): Y_prediction[0][i] = 1 if A[0][i] > 0.5 else 0 return Y_prediction def solve(X_train, Y_train, X_test, Y_test, num_iteration = 2000, learning_rate = 0.5) : w, b = init(X_train.shape[0]) params, grads, costs = optimize(w, b, X_train, Y_train, num_iteration, learning_rate) w = params["w"] b = params["b"] Y_perdiction_test = predict(w, b, X_test) Y_perdiction_train = predict(w, b, X_train) print("learning_rate = ", learning_rate) print("训练集准确性：" + format(100 - np.mean(abs(Y_perdiction_train - Y_train)) * 100), "%") print("测试集准确性：" + format(100 - np.mean(abs(Y_perdiction_test - Y_test)) * 100), "%") d = { "costs":costs, "Y_perdiction_test": Y_perdiction_test, "Y_perdiction_train": Y_perdiction_train, "w": w, "b": b, "learning_rate": learning_rate, "num_iteration": num_iteration } return d if __name__ == '__main__': train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset() # 压缩图像 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 # print(str(train_set_x_flatten.shape)) # 让数据位于0-1之间 train_set_x_flatten = train_set_x_flatten / 255 test_set_x_flatten = test_set_x_flatten / 255 print(str(train_set_x_flatten.shape)) # w, b, X, Y = np.array([[1], [2]]), 2, np.array([[1, 2], [3, 4]]), np.array([[1, 0]]) # grands, cost = propagate(w, b, X, Y) # print("dw = " + str(grands["dw"])) # print("db = " + str(grands["db"])) # print("cost = " + str(cost)) # w, b, X, Y = np.array([[1], [2]]), 2, np.array([[1, 2], [3, 4]]), np.array([[1, 0]]) # params, grads, costs = optimize(w, b, X, Y, num_iterations=100, learning_rate=0.009, print_cost=True) # #params, grands, costs = optimize(w, b, X, Y, num_iterations = 100, learning_rate = 0.09, print_cost = False) # print("w = " + str(params["w"])) # print("w = " + str(params["b"])) # print("dw = " + str(grads["dw"])) # print("db = " + str(grads["db"])) learning_rates = [0.01, 0.001, 0.0001] # learning_rates = [0.1, 0.01, 0.001] d = {} for i in learning_rates: d[str(i)] = solve(train_set_x_flatten, train_set_y, test_set_x_flatten, test_set_y, num_iteration=2000, learning_rate=i) for i in learning_rates: plt.plot(np.squeeze(d[str(i)]["costs"]), label = str(d[str(i)]["learning_rate"])) # 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() # plt.ylabel('cost') # plt.xlabel('iterations (per hundreds') # plt.title("Learning_rate" ) # plt.show() # index = 25 # plt.imshow(train_set_x_orig[index]) # plt.show() # print ("It is a" + classes[np.squeeze(train_set_y[:,index])].decode("utf8")) # See PyCharm help at https://www.jetbrains.com/help/pycharm/