TensorFlow 2.x

Eager Execution is enabled by default, so just call.numpy() on the Tensor object.

import tensorflow as tfa = 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)

SeeNumPy Compatibility for more. It is worth noting (from the docs),

Numpy array may share a 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 theAttributeError: '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, calltf.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 throughtf.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 alsoTF 2.0 Symbols Map for a mapping of the old API to the new one.

Any tensor returned bySession.run oreval is a NumPy array.

>>> print(type(tf.Session().run(tf.constant([1,2,3]))))<class 'numpy.ndarray'>

Or:

>>> sess = tf.InteractiveSession()>>> print(type(tf.constant([1,2,3]).eval()))<class 'numpy.ndarray'>

Or, equivalently:

>>> sess = tf.Session()>>> with sess.as_default():>>>    print(type(tf.constant([1,2,3]).eval()))<class 'numpy.ndarray'>

EDIT: Notany tensor returned bySession.run oreval() is a NumPy array. Sparse Tensors for example are returned as SparseTensorValue:

>>> print(type(tf.Session().run(tf.SparseTensor([[0, 0]],[1],[1,2]))))<class 'tensorflow.python.framework.sparse_tensor.SparseTensorValue'>

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

Regarding Tensorflow 2.x

The following generally works, since eager execution is activated by default:

import tensorflow as tfa = tf.constant([[1, 2], [3, 4]])                 b = tf.add(a, 1)print(a.numpy())# [[1 2]#  [3 4]]

However, since a lot of people seem to be posting the error:

AttributeError: 'Tensor' object has no attribute 'numpy'

I think it is fair to mention that callingtensor.numpy() in graph mode willnot work. That is why you are seeing this error. Here is a simple example:

import tensorflow as tf@tf.functiondef add():  a = tf.constant([[1, 2], [3, 4]])                   b = tf.add(a, 1)  tf.print(a.numpy()) # throws an error!  return aadd()

A simple explanation can be foundhere:

Fundamentally, one cannot convert a graph tensor to numpy array because the graph does not execute in Python - so there is no NumPy at graph execution. [...]

It is also worth taking a look at the TFdocs.

Regarding Keras models with Tensorflow 2.x

This also applies toKeras models, which are wrapped in atf.function by default. If you really need to runtensor.numpy(), you can set the parameterrun_eagerly=True inmodel.compile(*), but this will influence the performance of your model.

You need to:

1. encode the image tensor in some format (jpeg, png) to binary tensor
2. evaluate (run) the binary tensor in a session
3. turn the binary to stream
4. feed to PIL image
5. (optional) displaythe image with matplotlib

Code:

import tensorflow as tfimport matplotlib.pyplot as pltimport PIL...image_tensor = <your decoded image tensor>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

Maybe you can try，this method:

import tensorflow as tfW1 = 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)

I have faced and solved thetensor->ndarray conversion in the specific case of tensors representing (adversarial) images, obtained withcleverhans 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 inputplaceholders. Tensor may work like a function that needs its input values (provided intofeed_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 isx in my case, but I suppose you should find out the right name for the inputplaceholder.x_input is a scalar value or array containing input data.

In my case also providingsess was mandatory.

My example also covers thematplotlib image visualization part, but this is OT.

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

You can use keras backend function.

import tensorflow as tffrom tensorflow.python.keras import backend sess = backend.get_session()array = sess.run(< Tensor >)print(type(array))<class 'numpy.ndarray'>

I hope it helps!

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))    #<class 'tensorflow.python.framework.ops.Tensor'>    tf.InteractiveSession()  # run an interactive session in Tf.

nnow if we want this tensor a to be converted into a numpy array

    a_np=a.eval()    print(type(a_np))    #<class 'numpy.ndarray'>

As simple as that!

If you see there is a method_numpy(),e.g for an EagerTensor simply call the above method and you will get an ndarray.

I managed to transform a TensorGPU into an np.array using the following :

np.array(tensor_gpu.as_cpu())

(using the TensorGPU directly would only lead to a single-element array containing the TensorGPU).

TensorFlow 1.x

Foldertf.1, just use the following commands:

a = tf.constant([[1, 2], [3, 4]])                 b = tf.add(a, 1)out = tf.multiply(a, b)out.eval(session=tf.Session())

And the output would be:

# array([[ 2,  6],#       [12, 20]], dtype=int32)

• python
• numpy
• tensorflow