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 vote103 views1 answer
Python code pycharm
Python
0 vote104 views2 answers
Remove repetitive characters from the specified column of a given DataFrame
Python
0 vote118 views1 answer
Tasks discord py
Python
0 vote124 views1 answer
Mathplotlib limit x-axis
Python
1 vote65 views1 answer
Get urls from any website use python
Python
0 vote120 views1 answer
Write a line to a text file using the write() function
Python
7 votes130 views3 answers
Python split string by specific word
Python
19 votes104 views1 answer
Find root directory of jupyter notebook
Python
3 votes98 views3 answers
Send dm to user discord.py
Python
0 vote104 views1 answer
How to show webcam in opencv
Python