tf.tile()用法

Candy_GL發表於2018-10-08

版權宣告:本文為博主原創文章,未經博主允許不得轉載。 https://blog.csdn.net/Eric_LH/article/details/79074583

tile() 平鋪之意,用於在同一維度上的複製

tf.tile(  
    input,     #輸入  
    multiples,  #同一維度上覆制的次數  
    name=None  
)
#  a = tf.constant([1,2],name='a') 
#  b= tf.tile(a,[1,2])
#  sess = tf.Session()  
#  print(sess.run(b))
# [[1,2]
   [1,2]]

error:ValueError: Shape must be rank 1 but is rank 2 for ‘Tile’ (op: ‘Tile’) with input shapes: [2], [2].

import tensorflow as tf
a = tf.constant([[1,2]],name='a')
b= tf.tile(a,[1,2])
sess = tf.Session()
print(sess.run(b))

output: 
[[1 2 1 2]]

import tensorflow as tf
a = tf.constant([[1,2]],name='a')
b= tf.tile(a,[2,1])
sess = tf.Session()
print(sess.run(b))

output: 
[[1 2] 
[1 2]]

參考部落格: 
http://blog.csdn.net/xwd18280820053/article/details/72867818

--------------------- 本文來自 Eric_LH 的CSDN 部落格 ,全文地址請點選:https://blog.csdn.net/eric_lh/article/details/79074583?utm_source=copy