繁体   English   中英

我的交叉熵函数实现有什么问题?

[英]What is the problem with my implementation of the cross-entropy function?

我正在学习神经网络,我想在 python 中编写一个函数cross_entropy 它被定义为

交叉熵

其中N是样本数, k是类别数, log是自然对数,如果样本i属于第j类,则t_i,j为 1,否则为0 ,而p_i,j是样本i所在的预测概率j级。 为了避免对数的数值问题,将预测剪裁到[10^{−12}, 1 − 10^{−12}]范围。

根据上面的描述,我通过将预测裁剪到[epsilon, 1 − epsilon]范围来写下代码,然后根据上面的公式计算 cross_entropy。

def cross_entropy(predictions, targets, epsilon=1e-12):
    """
    Computes cross entropy between targets (encoded as one-hot vectors)
    and predictions. 
    Input: predictions (N, k) ndarray
           targets (N, k) ndarray        
    Returns: scalar
    """
    predictions = np.clip(predictions, epsilon, 1. - epsilon)
    ce = - np.mean(np.log(predictions) * targets) 
    return ce

下面的代码将用于检查函数cross_entropy是否正确。

predictions = np.array([[0.25,0.25,0.25,0.25],
                        [0.01,0.01,0.01,0.96]])
targets = np.array([[0,0,0,1],
                  [0,0,0,1]])
ans = 0.71355817782  #Correct answer
x = cross_entropy(predictions, targets)
print(np.isclose(x,ans))

上面代码的输出是 False,也就是说我定义函数cross_entropy代码不正确。 然后我打印cross_entropy(predictions, targets) 它给出了0.178389544455 ,正确的结果应该是ans = 0.71355817782 有人可以帮我检查一下我的代码有什么问题吗?

您根本没有那么远,但请记住,您正在取 N 个总和的平均值,其中 N = 2(在本例中)。 所以你的代码可以是:

def cross_entropy(predictions, targets, epsilon=1e-12):
    """
    Computes cross entropy between targets (encoded as one-hot vectors)
    and predictions. 
    Input: predictions (N, k) ndarray
           targets (N, k) ndarray        
    Returns: scalar
    """
    predictions = np.clip(predictions, epsilon, 1. - epsilon)
    N = predictions.shape[0]
    ce = -np.sum(targets*np.log(predictions+1e-9))/N
    return ce

predictions = np.array([[0.25,0.25,0.25,0.25],
                        [0.01,0.01,0.01,0.96]])
targets = np.array([[0,0,0,1],
                   [0,0,0,1]])
ans = 0.71355817782  #Correct answer
x = cross_entropy(predictions, targets)
print(np.isclose(x,ans))

在这里,我认为如果你坚持使用np.sum()更清楚一些。 另外,我在np.log()添加了 1e-9 以避免在计算中出现 log(0) 的可能性。 希望这可以帮助!

注意:根据@Peter 的评论,如果您的 epsilon 值大于0 ,则1e-9的偏移量确实是多余的。

def cross_entropy(x, y):
    """ Computes cross entropy between two distributions.
    Input: x: iterabale of N non-negative values
           y: iterabale of N non-negative values
    Returns: scalar
    """

    if np.any(x < 0) or np.any(y < 0):
        raise ValueError('Negative values exist.')

    # Force to proper probability mass function.
    x = np.array(x, dtype=np.float)
    y = np.array(y, dtype=np.float)
    x /= np.sum(x)
    y /= np.sum(y)

    # Ignore zero 'y' elements.
    mask = y > 0
    x = x[mask]
    y = y[mask]    
    ce = -np.sum(x * np.log(y)) 
    return ce

def cross_entropy_via_scipy(x, y):
        ''' SEE: https://en.wikipedia.org/wiki/Cross_entropy'''
        return  entropy(x) + entropy(x, y)

from scipy.stats import entropy, truncnorm

x = truncnorm.rvs(0.1, 2, size=100)
y = truncnorm.rvs(0.1, 2, size=100)
print np.isclose(cross_entropy(x, y), cross_entropy_via_scipy(x, y))

暂无
暂无

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM