使用Keras创建自定义条件指标 [英] Creating custom conditional metric with Keras

问题描述

我正在尝试使用keras为我的神经网络创建以下指标:

I am trying to create the following metric for my neural network using keras:

自定义Keras指标

其中d = y_ {pred} -y_ {true}

where d=y_{pred}-y_{true}

y_ {pred}和y_ {true}都是向量

and both y_{pred} and y_{true} are vectors

使用以下代码:

将keras.backend导入为K

import keras.backend as K

def score(y_true, y_pred):
        d=(y_pred - y_true)
        if d<0:
            return K.exp(-d/10)-1
        else:
            return K.exp(d/13)-1

用于编译我的模型:

model.compile(loss='mse', optimizer='adam', metrics=[score])

我收到以下错误代码，但我无法纠正此问题.任何帮助将不胜感激.

I received the following error code and I have not been able to correct the issue. Any help would be appreciated.

raise TypeError(使用tf.Tensor作为Python bool不是 允许的. "使用if t is not None:而不是if t:来测试是否 定义了张量，并使用TensorFlow操作，例如"

raise TypeError("Using a tf.Tensor as a Python bool is not allowed. " "Use if t is not None: instead of if t: to test if a " "tensor is defined, and use TensorFlow ops such as "

TypeError:不允许将tf.Tensor用作Python bool.使用 if t is not None:而不是if t:来测试是否定义了张量， 并使用诸如tf.cond之类的TensorFlow操作来执行子图 以张量的值为条件.

TypeError: Using a tf.Tensor as a Python bool is not allowed. Use if t is not None: instead of if t: to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.

推荐答案

您提供的指标不是每次都会执行的函数，而是需要评估的函数(计算图)的构造.因此，它必须是确定性的.

The metric you are providing is not a function that gets executed each time, but rather a construction of the function (computational graph) that needs to be evaluated. So it needs to be deterministic.

尝试:

def score(y_true, y_pred):
    d = y_pred - y_true
    mask = K.less(y_pred, y_true)  # element-wise True where y_pred < y_pred
    mask = K.cast(mask, K.floatx())  # cast to 0.0 / 1.0
    s = mask * (K.exp(-d / 10) - 1) + (1 - mask) * (K.exp(d / 13) - 1)  
    # every i where mask[i] is 1, s[i] == (K.exp(-d / 10) - 1)
    # every i where mask[i] is 0, s[i] == (K.exp(d / 13) - 1)
    return s

这篇关于使用Keras创建自定义条件指标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！