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 vote172 views1 answer
Change month name in python
Python
0 vote165 views1 answer
Python install pylab
Python
0 vote195 views1 answer
ModuleNotFoundError: No module named 'rest_auth'
Python
2 votes179 views3 answers
Pandas select by list of values in column
Python
0 vote166 views1 answer
Python format inverse
Python
0 vote185 views1 answer
Set defualt to none django
Python
1 vote173 views1 answer
Python import all words
Python
3 votes238 views1 answer
Django queryset group by
Python Django
0 vote178 views1 answer
Circular heatmap python
Python
0 vote130 views1 answer
Fibonacci sequence in python
Python