How do I convert a EagerTensor into a numpy array in Tensorflow?

In TensorFlow, converting an EagerTensor to a NumPy array is straightforward. This can be achieved by using the numpy() method. When working in eager execution mode (which is the default in TensorFlow 2.x), each Tensor object has a numpy() method that converts the EagerTensor to a NumPy array.

Here is a specific example demonstrating how to perform the conversion:

python
import tensorflow as tf

# Ensure eager execution mode is enabled
tf.executing_eagerly()

# Create a Tensor
tensor = tf.constant([[1, 2, 3], [4, 5, 6]])

# Convert to NumPy array using the .numpy() method
numpy_array = tensor.numpy()

# Print the converted NumPy array
print(numpy_array)

The output should be:

shell
[[1 2 3]
 [4 5 6]]

This example illustrates how to simply convert an EagerTensor in TensorFlow to a NumPy array. This is very useful when handling data and using libraries that only accept NumPy arrays as input.