How do I convert a Tensorflow Tensor to a NumPy Array?

Convert a Tensor to Numpy Array in Tensorflow

In Tensorflow, converting a tensor into a numpy array is straightforward. Here's how:

<code class="python">import tensorflow as tf

a = tf.constant([[1, 2], [3, 4]])
b = tf.add(a, 1)

a_numpy = a.numpy()  # Convert tensor 'a' to numpy array
b_numpy = b.numpy()  # Convert tensor 'b' to numpy array

print(a_numpy)
# [[1 2]
#  [3 4]]
print(b_numpy)
# [[2 3]
#  [4 5]]</code>

Notes:

• In Tensorflow 2.x, Eager Execution is enabled by default. So, you can simply call .numpy() on the tensor object.
• If you're getting an AttributeError about the .numpy() attribute, make sure that TF 2.0 is installed correctly and Eager Execution is enabled.
• Numpy arrays share memory with their corresponding tensors. Changes made to one are reflected in the other.
• If Eager Execution is disabled, you can build a graph and use tf.compat.v1.Session to execute it.

The above is the detailed content of How do I convert a Tensorflow Tensor to a NumPy Array?. For more information, please follow other related articles on the PHP Chinese website!