尝试对猫和狗的数据进行逻辑回归，但它给我除以零/nan尝试添加一些 val 来花费仍然相同的结果

问题描述

这是一个简单的模型：

import numpy as np
import copy

def sigmoid(z):
    return 1/(1+np.exp(-z))

我将权重和偏差初始化为零 此函数为 w 创建一个形状为 (dim,1) 的零向量，并将 b 初始化为 0。

参数： dim -- 我们想要的 w 向量的大小（或本例中的参数数量）

返回： w -- 形状的初始化向量 (dim,1) b -- 类型为 float 的初始化标量（对应于偏差）

def initialize_with_zeros(dim):
        w = np.zeros((dim,1))
        b = 0.
        return w,b

该函数用于向前和向后传递

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

    m = X.shape[1]
    # epsilon = 1e-5
    A = sigmoid(np.dot(w.T,X) + b)
    cost = (-1/m) * (np.dot(Y,np.log(A).T) + np.dot((1-Y),np.log(1-A).T))

    dw = 1 / m *(np.dot(X,(A - Y ).T))
    db = 1/m * (np.sum(A-Y))
    
    cost = np.squeeze(np.array(cost))
    
    grads = {"dw": dw,"db": db}
    
    return grads,cost

该函数用于更新参数

def optimize(w,Y,num_iterations=100,learning_rate=0.009,print_cost=False):
    w = copy.deepcopy(w)
    b = copy.deepcopy(b)

    costs = []
    for i in range(num_iterations):

        #gradient and cost calculations
        grads,cost = propagate(w,Y)

        #retrieve derivatives from grads
        dw = grads["dw"]
        db = grads["db"]

        #update 
        w = w - learning_rate * dw
        b = b - learning_rate * db

        #record cost every 100th iterations
        if i%100==0:
            costs.append(cost)

            if print_cost:
                print("cost after %i:%f" %(i,cost))
    
    params = {"w": w,"b": b}
    
    grads = {"dw": dw,"db": db}
    
    return params,grads,costs

该函数用于预测结果

def predict(w,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]):
        if A[0][i] > 0.5:
            Y_prediction[0][i] = 1.0
        else:
            Y_prediction[0][i] = 0.0

    return Y_prediction

逻辑回归模型：

def logisticregressionmodel(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,costs =  optimize(w,X_train,num_iterations,learning_rate,print_cost)
    
    w = parameters["w"]
    b = parameters["b"]
    
    Y_prediction_test = predict(w,X_test)
    Y_prediction_train = predict(w,X_train)

    # Print train/test Errors
    if print_cost:
        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


#result
 cost after 0:0.693147
cost after 100:nan
cost after 200:nan
cost after 300:nan
cost after 400:nan
cost after 500:nan
cost after 600:nan
cost after 700:nan
cost after 800:nan

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）