Tensorflow to numpy

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()

Turn numpy function into tensorflow

tf.numpy_function(    func, inp, Tout, name=None)

Source: tensorflow.org

Similar codes

0 vote363 views1 answer
Python textbox
Python
2 votes351 views2 answers
What is role of ALLOWED_HOSTs in Django
Python Django
0 vote353 views1 answer
Pandas check if any of the values in one column exist in another
Python
1 vote373 views1 answer
Rename one dataframe column python
Python
2 votes389 views1 answer
How to reomve certain row from dataframe pandas
Python
2 votes405 views1 answer
Python get ip from hostname
Python
0 vote354 views1 answer
Python hangman
Python
0 vote392 views1 answer
Matplotlib set y lim
Python
22 votes335 views3 answers
Python except error as e
Python
11 votes375 views4 answers
Add conda env to jupyter
Python