问题描述
我有一个用于多标签分类问题的CNN，并且使用 tf.nn.sigmoid_cross_entropy_with_logits 作为损失函数.
I have a CNN for a multilabel classification problem and as a loss function I use the tf.nn.sigmoid_cross_entropy_with_logits .
从 交叉熵方程我希望输出是每个类的概率但相反，我在(-∞，∞)中出现了浮点数.
From the cross entropy equation I would expect that the output would be probabilities of each class but instead I get floats in the (-∞, ∞) .
经过一番谷歌搜索后，我发现由于进行了一些内部规范化操作，每行对数在被送入方程式之前都可以解释为概率.
After some googling I found that due to some internal normalizing operation each row of logits is interpretable as probability before being fed to the equation.
我很困惑如何实际输出后验概率而不是浮点数来绘制ROC.
I'm confused about how I can actually output the posterior probabilities instead of floats in order to draw a ROC.
推荐答案
tf.sigmoid(logits)为您提供了概率.
您可以在 tf.nn.sigmoid_cross_entropy_with_logits 是将logit归一化为概率的函数.
You can see in the documentation of tf.nn.sigmoid_cross_entropy_with_logits that tf.sigmoid is the function that normalizes the logits to probabilities.
这篇关于Tensorflow:S形交叉熵损失产生的输出概率的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！