如果tensor是用呼叫tensorflow框架定義的，那麼用 tensor_name.shape 即可返回tensorflow 的維數：

>>> import tensorflow as tf 
>>> a=tf.constant([  
...         [[1.0,2.0,3.0,4.0],  
...         　[5.0,6.0,7.0,8.0],  
...         　[8.0,7.0,6.0,5.0],  
...         　[4.0,3.0,2.0,1.0]],  
...         [[4.0,3.0,2.0,1.0],  
...          [8.0
 
,7.0,6.0,5.0],  
...          [1.0,2.0,3.0,4.0],  
...          [5.0,6.0,7.0,8.0]]  
...     ])
>>> a.shape
TensorShape([Dimension(2), Dimension(4), Dimension(4)])

  也可通過呼叫 numpy 來返回 tensor 的維數：

>>> import numpy as np
>>> np.shape(a)
TensorShape([Dimension(2), Dimension(4), Dimension(4
 
)])