Python Tensorflow:矩阵乘法和加法期间的nan

我正在使用一个函数（ndegree_poly），它得到一个张量和一个权重数组，并从中计算多项式的结果

代码似乎很简单，但当阶数增加，或者函数重复多次时，结果张量包含一组NaN和Inf。INF是合理的。但是，如果数字真的越来越小，它们不应该变成零，而不是nan吗

import tensorflow as tf

function_degree = 10

def ndegree_poly(x, a, degree=6):
        op = tf.add_n([tf.multiply(tf.pow(x, i), a[i]) for i in range(1, degree)])
        return tf.add(op, a[0])

with tf.Session() as sess:
    poly_weight = tf.Variable(tf.random_normal([function_freedom, 1, 5]))

    mat = tf.Variable(tf.random_normal([2, 5]))

    result0 = ndegree_poly(mat, poly_weight, function_degree)
    result1 = ndegree_poly(result0, poly_weight, function_degree)
    result2 = ndegree_poly(result1, poly_weight, function_degree)
    result3 = ndegree_poly(result2, poly_weight, function_degree)
    result4 = ndegree_poly(result3, poly_weight, function_degree)


    sess.run(tf.global_variables_initializer())
    print(sess.run(result4))

它打印：

[[-0.28569764         nan         nan         nan        -inf]
 [        nan         nan  3.55561209         nan  0.53827095]]

---

nan

值不是来自非常小的系数，它只是尝试这样做的“自然”结果∞ - ∞, 因为系数来自正态分布，所以是正态和负态的

import math
import tensorflow as tf

tf_inf = tf.constant(inf)
res = tf_inf - tf_inf
with tf.Session() as sess:
    print(sess.run(res))

>>> nan

---

谢谢，我忘了考虑