更新时间:2023-02-02 17:28:20
您的神经网络至少存在一个问题,该问题会使您的结果概率产生偏差:模型输出是最后一层的sigmoid
本身是
There's at least one problem with your neural network that skews your result probabilities: the model output is the sigmoid
of the last layer which itself is a sigmoid
.
这意味着您的登录信息(即原始分数)在[0, 1]
中,因此最终概率是在[0, 1]
范围而不是[-inf, inf]
上计算的.
This means that your logit (i.e., the raw score) is in [0, 1]
, so the final probability is computed on a [0, 1]
range, not [-inf, inf]
.
如上图所示,这使得结果概率为 大于0.5.
As you can see from the graph above, this makes the results probability to be greater than 0.5.
解决方案:尝试使用没有最后一个sigmoid
的同一网络.
Solution: try the same network without the last sigmoid
.