tf.stack和tf.unstack

 1 import tensorflow as tf
 2 
 3 a = tf.constant([1,2,3])
 4 b = tf.constant([4,5,6])
 5 
 6 c1 = tf.stack([a,b],axis=0)
 7 c2 = tf.stack([a,b],axis=1)
 8 #take c2 for example showing results of unstack
 9 d1 = tf.unstack(c2,axis=0) # Return: The list of Tensor objects unstacked from value.
10 d2 = tf.unstack(c2,axis=1)
11 
12 with tf.Session() as sess:
13     print('c1(with shape:{}):\n{}'.format(c1.shape, sess.run(c1)))
14     print('c2(with shape:{}):\n{}'.format(c2.shape, sess.run(c2)))
15     
16     print('d1(with length:{}):\n{}'.format(len(d1), sess.run(d1)))
17     print('d2(with length:{}):\n{}'.format(len(d2), sess.run(d2)))

运行结果:

官方API:

https://www.tensorflow.org/api_docs/python/tf/stack

https://www.tensorflow.org/api_docs/python/tf/unstack

 

posted @ 2018-04-25 16:47  wxiaoli  阅读(342)  评论(0编辑  收藏  举报