问题描述
我尝试按如下方法建立自己的损失函数
I try to build up my own loss function as follows
import numpy as np
from keras import backend as K
def MyLoss(self, x_input, x_reconstruct):
a = np.copy(x_reconstruct)
a = np.asarray(a, dtype='float16')
a = np.floor(4*a)/4
return K.mean(K.square(a - x_input), axis=-1)`
在编译中,它说ValueError:设置具有序列的数组元素
In compilation, it saysValueError: setting an array element with a sequence
x_input和x_reconstruct都是[m,n,1]个np数组.实际上,最后一行代码是直接从Keras的内置MSE损失函数复制的.
Both x_input and x_reconstruct are [m, n, 1] np arrays. The last line of code is actually copied directly from Keras' built-in MSE loss function.
我还假设每个样本都计算出损失.如果输入和重构输入的尺寸均为[m,n,1],则Keras内置损耗的结果也将是矩阵大小[m,n].那么为什么它可以正常工作?
Also, I suppose loss is calculated per sample. If dimensions of the input and reconstructed input are both [m, n, 1], the result of Keras' built-in loss will also be a matrix sized [m, n]. So why does it work properly?
然后我尝试直接使用np的功能
I then tried to us np's functions directly by
def MyLoss(self, x_input, x_reconstruct):
a = np.copy(x_reconstruct)
a = np.asarray(a, dtype=self.precision)
a = np.floor(4*a)/4
Diff = a - x_input
xx = np.mean(np.square(Diff), axis=-1)
yy = np.sum(xx)
return yy
但是错误仍然存在.我犯了什么错误?应该如何编写代码?
yet the error persists. What mistake did I make? How should write the code?
曾从在详细介绍Keras ,我尝试了以下
def MyLoss(self, x_input, x_reconstruct):
if self.precision == 'float16':
K.set_floatx('float16')
K.set_epsilon(1e-4)
a = K.cast_to_floatx(x_input)
a = K.round(a*4.-0.5)/4.0
return K.sum(K.mean(K.square(x_input-a), axis=-1))
但是发生同样的错误
推荐答案
您不能在丢失中使用numpy
数组.您必须使用TensorFlow
或Keras
后端操作.试试这个吧:
You can not use numpy
arrays in your loss. You have to use TensorFlow
or Keras
backend operations. Try this maybe:
import tensorflow as tf
import keras.backend as K
def MyLoss(x_input, x_reconstruct):
a = tf.cast(x_input, dtype='tf.float16')
a = tf.floor(4*a)/4
return K.mean(K.square(a - x_input), axis=-1)
这篇关于建立自定义损失函数时的错误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!