限制Keras层中参数的总和 [英] Constraint on the sum of parameters in Keras Layer

问题描述

我想在图层的参数上添加自定义约束.我编写了一个具有两个可训练参数a和b s.t的自定义激活层: activation_fct = a * fct()+ b * fct().我需要使参数的总和(a + b)等于1，但是我不知道如何编写这样的约束.你能给我一些建议吗?

I want to add custom constraints on the parameters of a layer. I write a custom activation layer with two trainable parameters a and b s.t: activation_fct = a*fct() + b*fct(). I need to have the sum of the parameters (a+b) equal to 1 but I don't know how to write such a constraint. Can you give me some advices ?

先谢谢了.

推荐答案

您可以使用一个权重而不是两个权重，并使用以下自定义约束:

You can have a single weight instead of two, and use this custom constraint:

import keras.backend as K

class Between_0_1(keras.constraints.Constraint):
    def __call__(self, w):
        return K.clip(w, 0, 1)

然后在构建权重时，仅构建a并使用约束.

Then when building the weights, build only a and use the constraints.

def build(self, input_shape):
    self.a = self.add_weight(name='weight_a', 
                                  shape=(1,),
                                  initializer='uniform',
                                  constraint = Between_0_1(), 
                                  trainable=True)

    #if you want to start as 0.5
    K.set_value(self.a, [0.5])

    self.built = True

在 call 中， b = 1-a :

def call(self, inputs, **kwargs):
    #do stuff
    ....

    return (self.a * something) +  ((1-self.a)*another_thing)

---

您也可以尝试@MatusDubrava softmax 方法，但是在这种情况下，您的权重必须具有形状(2，)，并且没有约束:

---

You can alsto try @MatusDubrava softmax approach, but in this case your weights need to have shape (2,), and no constraint:

def build(self, input_shape):
    self.w = self.add_weight(name='weights', 
                              shape=(2,),
                              initializer='zeros',
                              trainable=True)
    self.build = True

def call(self, inputs, **kwargs):
    w = K.softmax(self.w)

    #do stuff
    ....

    return (w[0] * something ) + (w[1] * another_thing)

这篇关于限制Keras层中参数的总和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！