Printing a specific dimension of a tensor in tensorflow

Question

I have a tensor x of shape (4,64,5,5). How can I print (or just visualize) the content of a specific dimension?

What I'm trying to do is

with tf.Session() as sess: print(x[0,:,:,:].eval()) 

but I got the following error:

FailedPreconditionError: Error while reading resource variable dense_2/kernel from Container: localhost. This could mean that the variable was uninitialized. Not found: Container localhost does not exist. (Could not find resource: localhost/dense_2/kernel)

I'm using Tensorflow

1.14

Answer 1

I tried the same in colab in Tensorflow version 1.14 using tf.ones(shape=(4,64,5,5)). It is working fine. Here's the code:

! pip install tensorflow==1.14
import tensorflow as tf
print(tf.__version__)

x=tf.ones(shape=(4,64,5,5))
with tf.Session() as sess: print(x[:,0,0,0].eval())

Output:

1.14.0
[1. 1. 1. 1.]

Let us know if the issue still persists. Thanks!