Convert a tensor to numpy array in Tensorflow?

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.

Related Posts:

  1. Convert a tensor to numpy array in Tensorflow?
  2. Convert a tensor to numpy array in Tensorflow?
  3. What is the difference between np.mean and tf.reduce_mean?
  4. RuntimeError: module compiled against API version 0xc but this version of numpy is 0xb
  5. TypeError: only integer scalar arrays can be converted to a scalar index with 1D numpy indices array
  6. Import Error: No module named numpy
  7. Difference between import numpy and import numpy as np
  8. why numpy.ndarray is object is not callable in my simple for python loop
  9. numpy division with RuntimeWarning: invalid value encountered in double_scalars
  10. Numpy ValueError: setting an array element with a sequence. This message may appear without the existing of a sequence?
  11. How do I create an empty array/matrix in NumPy?
  12. numpy division with RuntimeWarning: invalid value encountered in double_scalars
  13. Converting list to numpy array
  14. Could not find a version that satisfies the requirement tensorflow
  15. How do you do natural logs (e.g. “ln()”) with numpy in Python?
  16. How do I read CSV data into a record array in NumPy?
  17. How to normalize a NumPy array to a unit vector?
  18. ImportError: numpy.core.multiarray failed to import
  19. Factorial in numpy and scipy
  20. ImportError: numpy.core.multiarray failed to import
  21. How to count the occurrence of certain item in an ndarray?
  22. size of NumPy array
  23. Python Pandas – Missing required dependencies [‘numpy’] 1
  24. ‘DataFrame’ object has no attribute ‘sort’
  25. TypeError: cannot unpack non-iterable int objec
  26. Using Numpy Vectorize on Functions that Return Vectors
  27. Use a.any() or a.all()
  28. ‘End of statement expected’ in pycharm
  29. Most efficient way to map function over numpy array
  30. Tensorflow: why ‘pip uninstall tensorflow’ cannot find tensorflow
  31. Installing tensorflow with anaconda in windows
  32. initialize a numpy array
  33. error: Failed to load the native TensorFlow runtime
  34. Can I run Keras model on gpu?
  35. Cannot convert list to array: ValueError: only one element tensors can be converted to Python scalars
  36. How can I use numpy.correlate to do autocorrelation?
  37. Calculating Covariance with Python and Numpy
  38. How to access the ith column of a NumPy multidimensional array?
  39. Dump a NumPy array into a csv file
  40. Python: find position of element in array
  41. What is the difference between sparse_categorical_crossentropy and categorical_crossentropy?
  42. Inverse of a matrix using numpy
  43. How to convert a PIL Image into a numpy array?
  44. Overcome ValueError for empty array
  45. numpy with python: convert 3d array to 2d
  46. Python: slicing a multi-dimensional array
  47. pip3: command not found
  48. Pytorch reshape tensor dimension
  49. How to remove specific elements in a numpy array
  50. Add single element to array in numpy
  51. Overflow / math range error for log or exp
  52. Creating a Pandas DataFrame from a Numpy array: How do I specify the index column and column headers?
  53. Overflow Error in Python’s numpy.exp function
  54. How do you get the magnitude of a vector in Numpy?
  55. No Module Named ‘_pywrap_tensorflow_internal’
  56. How to calculate rolling / moving average using python + NumPy / SciPy?
  57. ValueError: object too deep for desired array while using convolution
  58. Make list of arrays in python
  59. Import Error: No module named numpy Anaconda
  60. Dictionary in a numpy array?
  61. RuntimeWarning: divide by zero encountered in log
  62. pandas create new column based on values from other columns / apply a function of multiple columns, row-wise
  63. Error NameError: name ‘np’ is not defined
  64. How to fix “TypeError: len() of unsized object”
  65. Numpy.dot TypeError: Cannot cast array data from dtype(‘float64’) to dtype(‘S32’) according to the rule ‘safe’
  66. NumPy array is not JSON serializable
  67. How to calculate a Gaussian kernel matrix efficiently in numpy?
  68. How to get the unit vector from a numpy array
  69. Does Numpy automatically detect and use GPU?
  70. How can I check whether a numpy array is empty or not?
  71. “Divide by zero encountered in log” when not dividing by zero
  72. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  73. Good ways to “expand” a numpy ndarray?
  74. TypeError: ‘numpy.float64’ object does not support item assignment
  75. Official abbreviation for: import scipy as sp/sc
  76. Efficiently sorting a numpy array in descending order?
  77. How to plot an array in python?
  78. How to create a numpy array of lists?
  79. How to fix ‘RuntimeWarning: divide by zero encountered in double_scalars’
  80. IndexError: index 2 is out of bounds for axis 0 with size 2
  81. Tensorflow 2.0 – AttributeError: module ‘tensorflow’ has no attribute ‘Session’
  82. Create numpy matrix filled with NaNs
  83. built-in range or numpy.arange: which is more efficient?
  84. Concat DataFrame Reindexing only valid with uniquely valued Index objects
  85. threshold in 2D numpy array
  86. What is the difference between ‘SAME’ and ‘VALID’ padding in tf.nn.max_pool of tensorflow?
  87. Numpy Resize/Rescale Image
  88. numpy array concatenation error: 0-d arrays can’t be concatenated
  89. How to print the full NumPy array, without truncation?
  90. Calculate weighted average using a pandas/dataframe
  91. How to install NumPy for Python 3.6
  92. Complex number troubles with numpy
  93. Filtering a NumPy Array
  94. How to install numpy to Python 3.5?
  95. How to downgrade tensorflow, multiple versions possible?
  96. Function to determine if two numbers are nearly equal when rounded to n significant decimal digits
  97. TypeError: zip argument #2 must support iteration
  98. CS231n: How to calculate gradient for Softmax loss function?
  99. How to zip two 1d numpy array to 2d numpy array [duplicate]
  100. numpy/scipy/ipython:Failed to interpret file as a pickle

Leave a Comment