Question

从Coursera的深度学习课程中，我实现了逻辑回归：

import numpy as np
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt

def sigmoid(z):

    s = 1 / (1 + np.exp(-z))

    return s

def initialize_with_zeros(dim):

    w = np.zeros(shape=(dim, 1))
    b = 0

    return w, b


def propagate(w, b, X, Y):

    m = X.shape[1]

    A = sigmoid(np.dot(w.T, X) + b)  # compute activation
    cost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A)))  # compute cost

    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

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  # need to broadcast
        b = b - learning_rate * db

        if i % 100 == 0:
            costs.append(cost)

        # Print the cost every 100 training examples
        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

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]):
        # Convert probabilities a[0,i] to actual predictions p[0,i]
        ### START CODE HERE ### (≈ 4 lines of code)
        print(A)
        Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0
        ### END CODE HERE ###

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

    return Y_prediction

print ("sigmoid(0) = " + str(sigmoid(0)))
print ("sigmoid(9.2) = " + str(sigmoid(9.2)))

dim = 2
w, b = initialize_with_zeros(dim)
print ("w = " + str(w))
print ("b = " + str(b))

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)
print ("dw = " + str(grads["dw"]))
print ("db = " + str(grads["db"]))
print ("cost = " + str(cost))

params, grads, costs = optimize(w, b, X, Y, num_iterations= 10000, learning_rate = 0.01, print_cost = False)

print ("w = " + str(params["w"]))
print ("b = " + str(params["b"]))
print ("dw = " + str(grads["dw"]))
print ("db = " + str(grads["db"]))


print("predictions = " + str(predict(w, b, X)))

def model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=0.5, 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

我正在尝试使用包含5个样本的通用数据集，其中每个样本均包含4个元素：

train_set_x = np.array([[1,2,3,4],[4,3,2,1],[1,2,3,4],[4,3,2,1],[1,2,3,4]])
train_set_y = np.array([1,0,1,0,1])


test_set_x = np.array([[1,2,3,4],[4,3,2,1],[1,2,3,4],[4,3,2,1],[1,2,3,4]])
test_set_y = np.array([1,0,1,0,1])

train_set_x , train_set_y , test_set_x , test_set_y


d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)

但是会引发以下错误：

<ipython-input-409-bd4e233a8f4e> in propagate(w, b, X, Y)
     18 
     19     A = sigmoid(np.dot(w.T, X) + b)  # compute activation
---> 20     cost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A)))  # compute cost
     21 
     22     dw = (1 / m) * np.dot(X, (A - Y).T)

ValueError: operands could not be broadcast together with shapes (5,) (1,4)

我需要更改重量尺寸以计算成本值吗？

更新：

使用修改：

A = sigmoid(np.dot(X , w) + b)  # compute activation

导致错误：

<ipython-input-546-7a7980550834> in propagate(w, b, X, Y)
     20     m = X.shape[1]
     21 
---> 22     A = sigmoid(np.dot(X , w) + b)  # compute activation
     23     print('w.T' , w.T , 'w' , w, 'X' , X , 'Y' , Y , 'A' , A)
     24     cost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A)))  # compute cost

ValueError: shapes (5,4) and (5,1) not aligned: 4 (dim 1) != 5 (dim 0)

使用自定义数据集进行逻辑回归

0 个答案: