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 vote158 views1 answer
How to loop through glob.iglob iterator
Python
0 vote148 views1 answer
Python colorbar for circular heatmap
Python
0 vote139 views1 answer
Torchvision.transforms flatten
Python
0 vote143 views1 answer
Open python file with read write permissions
Python
0 vote188 views1 answer
How to catch stop itteration in generator as None
Python
4 votes146 views3 answers
Pandas df by row index
Python
0 vote148 views1 answer
How to format a matrix to align all rows python
Python
0 vote139 views1 answer
Requests save data to disk
Python
2 votes139 views1 answer
Python copy a 2D list
Python
0 vote147 views1 answer
Python string: .lower()
Python