Torch.nan_to_num

>>> x = torch.tensor([float('nan'), float('inf'), -float('inf'), 3.14])
>>> torch.nan_to_num(x)
tensor([ 0.0000e+00,  3.4028e+38, -3.4028e+38,  3.1400e+00])
>>> torch.nan_to_num(x, nan=2.0)
tensor([ 2.0000e+00,  3.4028e+38, -3.4028e+38,  3.1400e+00])
>>> torch.nan_to_num(x, nan=2.0, posinf=1.0)
tensor([ 2.0000e+00,  1.0000e+00, -3.4028e+38,  3.1400e+00])

Source: pytorch.org

Similar codes

0 vote108 views1 answer
Python soma números
Python
1 vote105 views1 answer
Python twilio certificate error
Python
1 vote70 views1 answer
Write a python program to split a given dictionary of lists into list of dictionaries.
Python
18 votes109 views6 answers
Factorial python
Python
-1 vote122 views2 answers
Reading tsv file in python
Python
0 vote109 views1 answer
Selenium page down key python
Python
1 vote102 views1 answer
Minimum from list of tuples
Python
2 votes108 views2 answers
How to make a python file run in the background
Python
1 vote143 views1 answer
Pip install django celery results
Python Django
1 vote116 views1 answer
Missingpy No module named 'sklearn.neighbors.base'
Python