Convert numpy array to tensor

Convert numpy to torch

torch.from_numpy(your_array)

Tf tensor from numpy

tf.convert_to_tensor(my_np_array, dtype=tf.float32)

Convert tensor to numpy array

import tensorflow as tf

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

a.numpy()
# array([[1, 2],
#        [3, 4]], dtype=int32)

b.numpy()
# array([[2, 3],
#        [4, 5]], dtype=int32)

tf.multiply(a, b).numpy()
# array([[ 2,  6],
#        [12, 20]], dtype=int32)

Source: stackoverflow.com

How do i turn a tensor into a numpy array

import torch

# Create PyTorch tensor
A_torch = torch.tensor([1, 2])

# Convert tensor to NumPy array
A_np = A_torch.numpy()

Convert numpy array to tensor

import numpy as np
import torch

numpy_array = np.array([1,3,5])
tensor_array = torch.from_numpy(numpy_array)

-1

Similar codes

21 votes151 views1 answer
Python date + days
Python
3 votes170 views3 answers
Virtualenv -p python3
Python
1 vote177 views1 answer
How to reference a file in python
Python
44 votes177 views6 answers
Pandas read csv file
Python
0 vote167 views1 answer
Pandas dataframe from multiple csv
Python
16 votes162 views4 answers
How to reverse array in python
Python
0 vote181 views1 answer
Index and reversing a sub list in python list
Python
1 vote166 views1 answer
Python if elif else in one line
Python
1 vote183 views2 answers
Django drop database postgres
Python
1 vote158 views1 answer
How to use query_params in get_object djangorestframework
Python