# TensorFlow – How to create a numpy ndarray from a tensor

• Last Updated : 01 Aug, 2020

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks.

To create a numpy array from Tensor, Tensor is converted to a proto tensor first.

Method Used:

• make_ndarray: This method accepts a TensorProto as input and returns a numpy array with same content as TensorProto.

Example 1:

## Python3

 # importing the libraryimport tensorflow as tf  # Initializing Inputvalue = tf.constant([1, 15, 10], dtype = tf.float64)  # Printing the Inputprint("Value: ", value)  # Converting Tensor to TensorProtoproto = tf.make_tensor_proto(value)  # Generating numpy arrayres = tf.make_ndarray(proto)  # Printing the resulting numpy arrayprint("Result: ", res)

Output:

Value:  tf.Tensor([ 1. 15. 10.], shape=(3, ), dtype=float64)
Result:  [ 1. 15. 10.]

Example 2: This example uses a Tensor with shape (2, 2) so the shape of resulting array will be (2, 2).

## Python3

 # importing the libraryimport tensorflow as tf  # Initializing Inputvalue = tf.constant([[1, 2], [3, 4]], dtype = tf.float64)  # Printing the Inputprint("Value: ", value)  # Converting Tensor to TensorProtoproto = tf.make_tensor_proto(value)  # Generating numpy arrayres = tf.make_ndarray(proto)  # Printing the resulting numpy arrayprint("Result: ", res)

Output:

Value:  tf.Tensor(
[[1. 2.]
[3. 4.]], shape=(2, 2), dtype=float64)
Result:  [[1. 2.]
[3. 4.]]

My Personal Notes arrow_drop_up