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

1 vote137 views1 answer
Returns the first n rows
Python
5 votes120 views4 answers
Django get or 404
Python
13 votes124 views1 answer
Selenium webdriver python
Python
21 votes129 views6 answers
Python simple server
Python
0 vote121 views1 answer
Django extend user model
Python
0 vote123 views1 answer
How to load a keras model with custom loss function
Python
5 votes134 views2 answers
Python pie chart
Python
1 vote127 views1 answer
File handling modes in python
Python
-1 vote128 views1 answer
AttributeError: 'list' object has no attribute 'dtypes'
Python
7 votes116 views2 answers
Numpy create a matrix of certain value
Python