tenworflow中top_k的理解

import tensorflow as tf;

 

A = [[0.8,0.6,0.3], [0.1,0.6,0.4]]

B = [1, 1]

out = tf.nn.in_top_k(A, B, 1)

with tf.Session() as sess:

 sess.run(tf.initialize_all_variables())

 print sess.run(out)

输出为[false true]'

理解因为k值为1就是说最大的一个概率索引是多少（分别是0，1）所以为[false true]

如果k=2那么就是（【0，1】，【1，2】）这是就该是[true true]，因为两个的索引都包含了1

参考https://blog.csdn.net/uestc_c2_403/article/details/73187915和https://blog.csdn.net/Enchanted_ZhouH/article/details/77200592