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

• Last Updated : 22 Mar, 2023

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

## Create a Numpy array from a torch.tensor

A Pytorch Tensor is basically the same as a NumPy array. This means it does not know anything about deep learning or computational graphs or gradients and is just a generic n-dimensional array to be used for arbitrary numeric computation.

### Example 1:

To create a Numpy array from Tensor, Tensor is converted to a tensor.numpy() first.

## Python3

 `# pip install torch``import` `torch``tensor ``=` `torch.tensor([``1``, ``2``, ``3``, ``4``, ``5``])` `np_a ``=` `tensor.numpy()`

Output:

`array([1, 2, 3, 4, 5])`

### Example 2:

To create a Numpy array from Tensor, Tensor is converted to a tensor.detach.numpy() first.

## Python3

 `# pip install torch``import` `torch``tensor ``=` `torch.tensor([``1``, ``2``, ``3``, ``4``, ``5``])` `np_b ``=` `tensor.detach().numpy()`

Output:

`array([1, 2, 3, 4, 5])`

### Example 3:

To create a Numpy array from Tensor, Tensor is converted to a tensor.detach().cpu().numpy() first.

## Python3

 `# pip install torch``import` `torch``tensor ``=` `torch.tensor([``1``, ``2``, ``3``, ``4``, ``5``])` `np_c ``=` `tensor.detach().cpu().numpy()`

Output:

`array([1, 2, 3, 4, 5])`

## Create a numpy ndarray from a Tensorflow.tensor

A torch in TensorFlow, as the name indicates, is a framework to define and run computations involving tensors. A tensor is a generalization of vectors and matrices to potentially higher dimensions.

### Example 1:

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

## Python3

 `# importing the library``import` `tensorflow as tf` `# Initializing Input``value ``=` `tf.constant([``1``, ``15``, ``10``], dtype ``=` `tf.float64)` `# Printing the Input``print``(``"Value: "``, value)` `# Converting Tensor to TensorProto``proto ``=` `tf.make_tensor_proto(value)` `# Generating numpy array``res ``=` `tf.make_ndarray(proto)` `# Printing the resulting numpy array``print``(``"Result: "``, res)`

Output:

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

### Example 2:

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

## Python3

 `# importing the library``import` `tensorflow as tf` `# Initializing Input``value ``=` `tf.constant([[``1``, ``2``], [``3``, ``4``]], dtype ``=` `tf.float64)` `# Printing the Input``print``(``"Value: "``, value)` `# Converting Tensor to TensorProto``proto ``=` `tf.make_tensor_proto(value)` `# Generating numpy array``res ``=` `tf.make_ndarray(proto)` `# Printing the resulting numpy array``print``(``"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