How to get Tensorflow tensor dimensions shape as int values

Question

Suppose I have a Tensorflow tensor  How do I get the dimensions  shape  of the tensor as integer values  I know there are two methods  tensor get shape   and tf shape tensor   but I can t get the shape values as integer int32 values   For example  below I ve created a 2-D tensor  and I need to get the number of rows and columns as int32 so that I can call reshape   to create a tensor of shape  num rows   num cols  1   However  the method tensor get shape   returns values as Dimension type  not int32   import tensorflow as tf import numpy as np  sess   tf Session       tensor   tf convert to tensor np array   1001 1002 1003   3 4 5     dtype tf float32   sess run tensor        array    1001    1002    1003                  3       4       5     dtype float32   tensor shape   tensor get shape       tensor shape   TensorShape  Dimension 2   Dimension 3        print tensor shape        2  3   num rows   tensor shape 0        num cols   tensor shape 1         tensor2   tf reshape tensor   num rows num cols  1         Traceback  most recent call last       File   lt stdin gt    line 1  in  lt module gt      File   usr local lib python2 7 site-packages tensorflow python ops gen array ops py   line 1750  in reshape       name name      File   usr local lib python2 7 site-packages tensorflow python framework op def library py   line 454  in apply op       as ref input arg is ref      File   usr local lib python2 7 site-packages tensorflow python framework ops py   line 621  in convert to tensor       ret   conversion func value  dtype dtype  name name  as ref as ref      File   usr local lib python2 7 site-packages tensorflow python framework constant op py   line 180  in  constant tensor conversion function       return constant v  dtype dtype  name name      File   usr local lib python2 7 site-packages tensorflow python framework constant op py   line 163  in constant       tensor util make tensor proto value  dtype dtype  shape shape       File   usr local lib python2 7 site-packages tensorflow python framework tensor util py   line 353  in make tensor proto        AssertCompatible values  dtype      File   usr local lib python2 7 site-packages tensorflow python framework tensor util py   line 290  in  AssertCompatible        dtype name  repr mismatch   type mismatch    name       TypeError  Expected int32  got Dimension 6  of type  Dimension  instead

User · Accepted Answer

To get the shape as a list of ints  do tensor get shape   as list     To complete your tf shape   call  try tensor2   tf reshape tensor  tf TensorShape  num rows num cols  1     Or you can directly do tensor2   tf reshape tensor  tf TensorShape  -1  1    where its first dimension can be inferred

User · Answer

for a 2-D tensor  you can get the number of rows and columns as int32 using the following code   rows  columns   map lambda i  i value  tensor get shape

User · Answer

Another simple solution is to use map   as follows  tensor shape   map int  my tensor shape   This converts all the Dimension objects to int

User · Answer

In later versions  tested with TensorFlow 1 14  there s a more numpy-like way to get the shape of a tensor  You can use tensor shape to get the shape of the tensor   tensor shape   tensor shape print tensor shape

User · Answer

2 0 Compatible Answer  In Tensorflow 2 x  2 1   you can get the dimensions  shape  of the tensor as integer values  as shown in the Code below   Method 1  using tf shape    import tensorflow as tf c   tf constant   1 0  2 0  3 0    4 0  5 0  6 0    Shape   c shape as list   print Shape       2 3    Method 2  using tf get shape      import tensorflow as tf c   tf constant   1 0  2 0  3 0    4 0  5 0  6 0    Shape   c get shape   as list   print Shape       2 3

User · Answer

Another way to solve this is like this   tensor shape 0  value   This will return the int value of the Dimension object

[python] How to get Tensorflow tensor dimensions (shape) as int values?

Examples related to python

Examples related to tensorflow

Examples related to machine-learning

Examples related to artificial-intelligence