Convert a tensor to numpy array in Tensorflow

Question

How to convert a tensor into a numpy array when using Tensorflow with Python bindings

User · Answer

Maybe you can try this method   import tensorflow as tf W1   tf Variable tf random uniform  1   -1 0  1 0   init   tf global variables initializer   sess   tf Session   sess run init  array   W1 eval sess  print  array

User · Answer

A simple example could be       import tensorflow as tf     import numpy as np     a tf random normal  2 3  0 0 1 0 dtype tf float32    sampling from a std normal     print type a         lt class  tensorflow python framework ops Tensor  gt      tf InteractiveSession      run an interactive session in Tf    n now if we want this tensor a to be converted into a numpy array      a np a eval       print type a np         lt class  numpy ndarray  gt    As simple as that

User · Answer

You can convert a tensor in tensorflow to numpy array in the following ways  First  Use np array your tensor  Second  Use your tensor numpy

User · Answer

You can use keras backend function   import tensorflow as tf from tensorflow python keras import backend   sess   backend get session   array   sess run  lt  Tensor  gt    print type array     lt class  numpy ndarray  gt    I hope it helps

User · Answer

You need to     encode the image tensor in some format  jpeg  png  to binary tensor  evaluate  run  the binary tensor in a session  turn the binary to stream   feed to PIL image    optional  displaythe image with matplotlib   Code   import tensorflow as tf import matplotlib pyplot as plt import PIL       image tensor    lt your decoded image tensor gt  jpeg bin tensor   tf image encode jpeg image tensor   with tf Session   as sess        display encoded back to image data     jpeg bin   sess run jpeg bin tensor      jpeg str   StringIO StringIO jpeg bin      jpeg image   PIL Image open jpeg str      plt imshow jpeg image    This worked for me  You can try it in a ipython notebook  Just don t forget to add the following line    matplotlib inline

User · Answer

TensorFlow 2 x Eager Execution is enabled by default  so just call  numpy   on the Tensor object  import tensorflow as tf  a   tf constant   1  2    3  4                     b   tf add a  1   a numpy     array   1  2             3  4    dtype int32   b numpy     array   2  3             4  5    dtype int32   tf multiply a  b  numpy     array    2   6             12  20    dtype int32   See NumPy Compatibility for more  It is worth noting  from the docs    Numpy array may share memory with the Tensor object  Any changes to one may be reflected in the other   Bold emphasis mine  A copy may or may not be returned  and this is an implementation detail based on whether the data is in CPU or GPU  in the latter case  a copy has to be made from GPU to host memory   But why am I getting AttributeError   Tensor  object has no attribute  numpy    A lot of folks have commented about this issue  there are a couple of possible reasons   TF 2 0 is not correctly installed  in which case  try re-installing   or TF 2 0 is installed  but eager execution is disabled for some reason  In such cases  call tf compat v1 enable eager execution   to enable it  or see below    If Eager Execution is disabled  you can build a graph and then run it through tf compat v1 Session  a   tf constant   1  2    3  4                     b   tf add a  1  out   tf multiply a  b   out eval session tf compat v1 Session          array    2   6             12  20    dtype int32  See also TF 2 0 Symbols Map for a mapping of the old API to the new one

User · Answer

Any tensor returned by Session run or eval is a NumPy array    gt  gt  gt  print type tf Session   run tf constant  1 2 3       lt class  numpy ndarray  gt    Or    gt  gt  gt  sess   tf InteractiveSession    gt  gt  gt  print type tf constant  1 2 3   eval      lt class  numpy ndarray  gt    Or  equivalently    gt  gt  gt  sess   tf Session    gt  gt  gt  with sess as default     gt  gt  gt     print type tf constant  1 2 3   eval      lt class  numpy ndarray  gt    EDIT  Not any tensor returned by Session run or eval   is a NumPy array  Sparse Tensors for example are returned as SparseTensorValue    gt  gt  gt  print type tf Session   run tf SparseTensor   0  0    1   1 2       lt class  tensorflow python framework sparse tensor SparseTensorValue  gt

User · Answer

I have faced and solved the tensor- ndarray conversion in the specific case of tensors representing  adversarial  images  obtained with cleverhans library tutorials   I think that my question answer  here  may be an helpful example also for other cases   I m new with TensorFlow  mine is an empirical conclusion   It seems that tensor eval   method may need  in order to succeed  also the value for input placeholders   Tensor may work like a function that needs its input values  provided into feed dict  in order to return an output value  e g   array out   tensor eval session sess  feed dict  x  x input     Please note that the placeholder name is x in my case  but I suppose you should find out the right name for the input placeholder   x input is a scalar value or array containing input data   In my case also providing sess was mandatory   My example also covers the matplotlib image visualization part  but this is OT

User · Answer

I was searching for days for this command   This worked for me outside any session or somthing like this     you get an array   your tensor eval session tf compat v1 Session    an array   a tensor eval session tf compat v1 Session      https   kite com python answers how-to-convert-a-tensorflow-tensor-to-a-numpy-array-in-python

User · Answer

If you see there is a method  numpy    e g for an EagerTensor simply call the above method and you will get an ndarray

User · Answer

To convert back from tensor to numpy array you can simply run  eval   on the transformed tensor

[python] Convert a tensor to numpy array in Tensorflow?

Examples related to python

Examples related to numpy

Examples related to tensorflow