参考链接:https://blog.csdn.net/u013733326/article/details/79702148
# 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 from testCases import * import sklearn import sklearn.datasets import sklearn.linear_model from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets np.random.seed(1) def sigmoid(z): return 1 / (1 + np.exp(-z)) def layer_sizes(X, Y): n_x = X.shape[0] n_y = Y.shape[0] n_h = 4 return n_x, n_h, n_y def init(nx, nh, ny): np.random.seed(2) w1 = np.random.randn(nh, nx) * 0.01 b1 = np.zeros(shape=(nh, 1)) w2 = np.random.randn(ny, nh) * 0.01 b2 = np.zeros(shape=(ny, 1)) assert w1.shape == (nh, nx) assert b1.shape == (nh, 1) assert w2.shape == (ny, nh) assert b2.shape == (ny, 1) paramters = { "w1": w1, "b1": b1, "w2": w2, "b2": b2 } return paramters # Press the green button in the gutter to run the script. def forward(X, paramters): w1 = paramters["w1"] b1 = paramters["b1"] w2 = paramters["w2"] b2 = paramters["b2"] # 前向传播 z1 = np.dot(w1, X) + b1 a1 = np.tanh(z1) z2 = np.dot(w2, a1) + b2 a2 = sigmoid(z2) assert a2.shape == (1, X.shape[1]) cache = { "z1": z1, "a1": a1, "z2": z2, "a2": a2 } return cache def cal_cost(Y, parameters, a2): m = Y.shape[1] w1 = parameters["w1"] w2 = parameters["w2"] logprobs = np.multiply(np.log(a2), Y) + np.multiply((1 - Y), np.log(1 - a2)) cost = -np.sum(logprobs) / m cost = float(np.squeeze(cost)) assert isinstance(cost, float) return cost def backward_propagation(paramters, cache, X, Y): m = Y.shape[1] w1 = paramters["w1"] w2 = paramters["w2"] a1 = cache["a1"] a2 = cache["a2"] dz2 = a2 - Y dw2 = 1 / m * np.dot(dz2, a1.T) db2 = 1 / m * np.sum(dz2, axis=1, keepdims=True) dz1 = np.multiply(np.dot(w2.T, dz2), 1 - np.power(a1, 2)) dw1 = 1 / m * np.dot(dz1, X.T) db1 = 1 / m * np.sum(dz1, axis=1, keepdims=True) grads = { "dw1": dw1, "db1": db1, "dw2": dw2, "db2": db2 } return grads def update(paramters, grads, learning_rate): w1, w2 = paramters["w1"], paramters["w2"] b1, b2 = paramters["b1"], paramters["b2"] dw1, dw2 = grads["dw1"], grads["dw2"] db1, db2 = grads["db1"], grads["db2"] w1 = w1 - learning_rate * dw1 b1 = b1 - learning_rate * db1 w2 = w2 - learning_rate * dw2 b2 = b2 - learning_rate * db2 paramters = { "w1": w1, "b1": b1, "w2": w2, "b2": b2 } return paramters def predict(parameters, X): cache = forward(X, parameters) a2 = cache["a2"] predictions = np.round(a2) return predictions def solve(X, Y, nh, num_iterations, learning_rate): parameters = init(X.shape[0], nh, Y.shape[0]) for i in range(num_iterations): cache = forward(X, parameters) cost = cal_cost(Y, parameters, cache["a2"]) grads = backward_propagation(parameters, cache, X, Y) parameters = update(parameters, grads, learning_rate) return parameters if __name__ == '__main__': # print_hi('PyCharm') X, Y = load_planar_dataset() hiden = [1, 2, 3, 4, 5, 10, 20, 30, 40, 50] for i, n_h in enumerate(hiden): print("nh = :", n_h) parameters = solve(X, Y, i, num_iterations=5000, learning_rate=0.5) plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y) plt.title("Decision Boundary for hidden layer size " + str(4)) predictions = predict(parameters, X) print('准确率: %d' % float((np.dot(Y, predictions.T) + np.dot(1 - Y, 1 - predictions.T)) / float(Y.size) * 100) + '%') plt.show() # X_assess = predict_test_case() # predictions = predict(parameters, X) # print(str(np.mean(predictions))) # plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral) # plt.show() # # print(X.shape) # shape_X = X.shape # shape_Y = Y.shape # m = Y.shape[1] # print("X的纬度为:" + str(shape_X)) # print("X的纬度为:" + str(shape_Y)) # print("数据集里面的数据有:" + str(m) + "个") # clf = sklearn.linear_model.LogisticRegressionCV() # clf.fit(X.T, Y.T.ravel()) # clf.fit(X.T, Y.T) # clf = sklearn.linear_model.LogisticRegressionCV() # clf.fit(X.T, Y.T) # plot_decision_boundary(lambda x: clf.predict(x), X, Y) # plt.title("Logistic Regression") # LR_predictions = clf.predict(X.T) # plt.show() # print("逻辑回归的准确性:%d" # % float((np.dot(Y, LR_predictions) + np.dot(1 - Y, 1 - LR_predictions)) / # float(Y.size) * 100) # + "%" + "(正确标记数据点所占的百分比)") # See PyCharm help at https://www.jetbrains.com/help/pycharm/
本站文章如无特殊说明,均为本站原创,如若转载,请注明出处:吴恩达《深度学习》第一课第三周编程作业(带一个隐藏层的分类问题) - Python技术站