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

1 vote331 views1 answer
Python read entire file as string
Python
1 vote315 views1 answer
Replace the jinja template value inside the dictionary python
Python
3 votes377 views2 answers
Interpreter in python
Python
1 vote306 views1 answer
Django update increment
Python
1 vote304 views1 answer
•ImportError: cannot import name 'tf_utils'
Python
1 vote360 views1 answer
How to add a cooment in python
Python
-1 vote331 views1 answer
What is admin.tabularinline django
Python
6 votes326 views6 answers
What is the best ide for python
Python
9 votes369 views3 answers
Python datetime get weekday name
Python
0 vote307 views1 answer
Series distict
Python