How to Convert a TensorFlow Tensor to a NumPy Array?

Converting Tensor to Numpy Array in Tensorflow

Tensorflow provides the flexibility to work with tensors, which can be converted into Numpy arrays when necessary. Understanding this conversion is crucial in bridging the gap between these two powerful data structures.

TensorFlow 2.x with Eager Execution

In TensorFlow 2.x, eager execution is enabled by default. To convert a tensor into a Numpy array, simply invoke the .numpy() method on the tensor object.

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

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

a.numpy()  # Returns the Numpy array representing the tensor a
b.numpy()  # Returns the Numpy array representing the tensor b</code>

TensorFlow 2.x with Graph Execution

If eager execution is disabled, one can build a graph and run it through a TensorFlow session to achieve the conversion.

<code class="python">a = tf.constant([[1, 2], [3, 4]])
b = tf.add(a, 1)

out = tf.multiply(a, b)
out.eval(session=tf.compat.v1.Session())  # Evaluates the graph and returns the Numpy array for out</code>

Important Note

It's worth noting that the Numpy array may share memory with the tensor object. Any changes to one may be reflected in the other. Therefore, it's best to exercise caution while modifying either the tensor or the Numpy array.

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