如何使用keras编写具有许多条件的条件? [英] How to write a conditional with many conditions using keras?

问题描述

我有以下自定义损失:

def Loss(y_true,y_pred):
    y_pred = relu(y_pred)
    z = k.maximum(y_true, y_pred)
    y_pred_negativo = Lambda(lambda x: -x)(y_pred)
    w = k.abs(add([y_true, y_pred_negativo])) 
    if k.sum(z) == 0.0:
        erro = 0.0
    elif k.sum(y_true) == 0.0 and k.sum(z) != 0:
        erro = 100
    else:
        erro = (k.sum(w)/k.sum(z))*100.0
    return erro

但是，正如您所看到的，我将numpy与张量条件混合在一起.因此，我必须以张量格式编写此条件.

However, as you can see, I'm mixing numpy with tensor conditional. Therefore, I have to write this conditional in a tensor format.

if k.sum(z) == 0.0:
    erro = 0.0
elif k.sum(y_true) == 0.0 and k.sum(z) != 0:
    erro = 100
else:
    erro = (k.sum(w)/k.sum(z))*100.0

我知道如何针对 if 格式进行操作，但是对于很多情况却不了解.谢谢！

I know how to do it for if else format, but not for this much of the conditions. Thanks!

推荐答案

以下是我自己对keras条件语句的定义.

Here comes my own definition of conditional statement in terms of keras.

def energia_perdida_tensorial(y_true,y_pred):
    y_pred = relu(y_pred)
    z = k.maximum(y_true, y_pred)
    y_pred_negativo = Lambda(lambda x: -x)(y_pred)
    w = k.abs(add([y_true, y_pred_negativo])) 
    erro = k.switch(k.equal(k.sum(z), 0.0), lambda: 0.0, lambda: (k.sum(w)/k.sum(z))*100.0)
    erro = k.switch(k.all([k.equal(k.sum(y_true), 0), k.greater(k.sum(z), 0)], axis=0), lambda: 100.0, lambda: erro)
    return erro

如果有任何错误或更优雅的定义方式，请做出贡献.

If is there anything wrong or a more elegant way of defining it, please make your contribuition.

这篇关于如何使用keras编写具有许多条件的条件?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IT屋！