一些要补的概念

交叉熵损失
https://blog.csdn.net/red_stone1/article/details/80735068

one-hot编码
import tensorflow as tf
index=[0,1,2,3]
one_hot=tf.one_hot(index,5)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print(sess.run(one_hot))
https://blog.csdn.net/LanboCSDN/article/details/78291785