3

我正在使用负二项分布对变量进行建模。我宁愿对分布的两个参数进行建模,而不是预测期望平均值。所以我的神经网络的输出层是由两个神经元组成的。为此,我需要编写一个自定义损失函数。但是下面的代码不起作用 - 似乎是迭代张量的问题。

对于负二项分布,我应该如何使用 Keras(和 TensorFlow)编写损失函数?

我只需要重写这段代码,代码对 TensorFlow 的张量友好。根据我得到的错误,也许tensorflow.map_fn可能会导致解决方案,但我没有运气。

这通常运行良好,但不适用于 Keras / Tensorflow

from scipy.stats import nbinom
from keras import backend as K
import tensorflow as tf

def loss_neg_bin(y_pred, y_true):

    result = 0.0
    for p, t in zip(y_pred, y_true):
        result += -nbinom.pmf(t, p[0], min(0.99, p[1]))

    return result

我得到的错误:

TypeError:张量对象仅在启用急切执行时才可迭代。要迭代此张量,请使用 tf.map_fn。

4

1 回答 1

2

你需要tf.map_fn实现循环和tf.py_func结束nbinom.pmf。例如:

from scipy.stats import nbinom
import tensorflow as tf

def loss_neg_bin(y_pred, y_true):
    result = 0.0
    for p, t in zip(y_pred, y_true):
        result += -nbinom.pmf(t, p[0], min(0.99, p[1]))
    return result

y_pred= [[0.4, 0.4],[0.5, 0.5]]
y_true= [[1, 2],[1, 2]]
print('your version:\n',loss_neg_bin(y_pred, y_true))

def loss_neg_bin_tf(y_pred, y_true):
    result = tf.map_fn(lambda x:tf.py_func(lambda p,t:-nbinom.pmf(t, p[0], min(0.99,p[1]))
                                           ,x
                                           ,tf.float64)
                       ,(y_pred,y_true)
                       ,dtype=tf.float64)
    result = tf.reduce_sum(result,axis=0)
    return result

y_pred_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
y_true_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
loss = loss_neg_bin_tf(y_pred_tf, y_true_tf)

with tf.Session() as sess:
    print('tensorflow version:\n',sess.run(loss,feed_dict={y_pred_tf:y_pred,y_true_tf:y_true}))

# print
your version:
 [-0.34313146 -0.13616026]
tensorflow version:
 [-0.34313146 -0.13616026]

另外,如果你使用tf.py_func负二项式计算概率质量函数作为损失反馈模型,你需要自己定义梯度函数。

更新——添加可微负二项式损失

的概率质量函数为nbinom

nbinom.pmf(k) = choose(k+n-1, n-1) * p**n * (1-p)**k

k >= 0根据scipy.stats.nbinom。_

所以我添加了可微分负二项式损失版本。

import tensorflow as tf

def nbinom_pmf_tf(x,n,p):
    coeff = tf.lgamma(n + x) - tf.lgamma(x + 1) - tf.lgamma(n)
    return tf.cast(tf.exp(coeff + n * tf.log(p) + x * tf.log(1 - p)),dtype=tf.float64)

def loss_neg_bin_tf_differentiable(y_pred, y_true):
    result = tf.map_fn(lambda x: -nbinom_pmf_tf(x[1]
                                                , x[0][0]
                                                , tf.minimum(tf.constant(0.99,dtype=tf.float64),x[0][1]))
                       ,(y_pred,y_true)
                       ,dtype=tf.float64)
    result = tf.reduce_sum(result,axis=0)
    return result

y_pred_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
y_true_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
loss = loss_neg_bin_tf_differentiable(y_pred_tf, y_true_tf)
grads = tf.gradients(loss,y_pred_tf)

y_pred= [[0.4, 0.4],[0.5, 0.5]]
y_true= [[1, 2],[1, 2]]
with tf.Session() as sess:
    print('tensorflow differentiable version:')
    loss_val,grads_val = sess.run([loss,grads],feed_dict={y_pred_tf:y_pred,y_true_tf:y_true})
    print(loss_val)
    print(grads_val)

# print
tensorflow differentiable version:
[-0.34313146 -0.13616026]
[array([[-0.42401619,  0.27393084],
       [-0.36184822,  0.37565048]])]
于 2019-04-24T03:22:40.767 回答