吴恩达 ---cat识别
import numpy as np import matplotlib.pyplot as plt import h5py import imageio from PIL import Image # '''加载数据集''' def load_dataset(): train_dataset = h5py.File('datasets/train_catvnoncat.h5', "r") train_set_x_orig = np.array(train_dataset["train_set_x"][:]) train_set_y_orig = np.array(train_dataset["train_set_y"][:]) test_dataset = h5py.File('datasets/test_catvnoncat.h5', 'r') test_set_x_orig = np.array(test_dataset["test_set_x"][:]) test_set_y_orig = np.array(test_dataset['test_set_y'][:]) classes = np.array(test_dataset["list_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 train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset() # 画出一个图像 index = 56 # plt.imshow(train_set_x_orig[index]) # plt.show() print("y= "+str(train_set_y[:, index])+ ", it's a '"+ classes[np.squeeze(train_set_y[:, index])].decode('utf-8')+"' picture.") m_train = train_set_y.shape[1] # number of training examples m_test = test_set_y.shape[1] # number of test examples num_px = train_set_x_orig.shape[1] # (=height, =width of a training image print("Number of training examples: "+str(m_train)) print("Number of test examples: "+str(m_test)) print("Height/Width of each image: "+str(num_px)) # 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 print("Train_set_x_flatten shape: "+str(train_set_x_flatten.shape)) print("Test_set_x_flatten shape: "+str(test_set_x_flatten.shape)) # standardize train_set_x = train_set_x_flatten / 255 test_set_x = test_set_x_flatten / 255 # sigmoid activation function def sigmoid(z): s = 1/(1 + np.exp(-z)) return s # initialize w and b 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 # calculate cost, dw,db def propagate(w, b, x, y): Z = np.dot(w.T, x)+b A = sigmoid(Z) m = x.shape[1] cost = (-1 / m) * np.sum(y * np.log(A) + (1-y) * (np.log(1-A))) dw = (1/m) * np.dot(x, (A-y).T) db = (1/m) * np.sum(A - y) cost = np.squeeze(cost) grads = {"dw": dw, "db": db} return grads, cost # update w,b 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.get("dw") db = grads.get("db") w -= (learning_rate * dw) b -= (learning_rate * db) if i % 100 == 0: costs.append(cost) if print_cost: print("Cost after iteration %i: is : %f" % (i, cost)) params = {"w": w, "b": b} grads = {"dw": dw, "db": db} return params, grads, costs # predict function def predict(w, b, X): w = w.reshape((X.shape[0], 1)) z = np.dot(w.T, X) + b A = sigmoid(z) m = X.shape[1] y_predict = np.zeros((1, m)) for i in range(A.shape[1]): y_predict[0, i] = 1 if A[0, i] > 0.5 else 0 return y_predict # combine whole function def model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=.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) 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=1000, learning_rate=0.005, print_cost=True) # 更换新图片进行测试 my_image = 'timg.jpg' fname = 'D:/BaiduNetdiskDownload/'+my_image image = np.array(imageio.imread(fname)) my_image = np.array(Image.fromarray(image).resize(size=(num_px, num_px))).reshape((1, num_px*num_px*3)).T my_predicted_image = predict(d['w'], d['b'], my_image) print('y = ' + str(np.squeeze(my_predicted_image)) + ', your algorithm predicts a \"'+classes[int( np.squeeze(my_predicted_image)), ].decode("utf-8") + '\" picture') plt.imshow(image) plt.show() # # 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() ''' 下面的代码用于比较不同的学习率 ''' # learning_rates = [0.01, 0.001, 0.0001] # # models = {} # for i in learning_rates: # print("learning rate is: "+str(i)) # models[str(i)] = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations=1500, learning_rate=i, # print_cost=False) # print('\n ------------------------------------\n') # # 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()