PyTorch torch.fmin Function
Pytorch torch Reference Manual
torch.fminIt is a function in PyTorch for element-wise minimum (ignoring NaN). When the input contains NaN, torch.minimum returns NaN, while torch.fmin ignores NaN and returns the non-NaN value.
Function Definition
torch.fmin(input, other)
Usage Example
Example
import torch
# Create a tensor containing NaN
x = torch.tensor([3.0, float('nan'), 4.0])
y = torch.tensor([1.0, 5.0, 2.0])
# Element-wise minimum (ignoring NaN)
result = torch.fmin(x, y)
print(result)
# Create a tensor containing NaN
x = torch.tensor([3.0, float('nan'), 4.0])
y = torch.tensor([1.0, 5.0, 2.0])
# Element-wise minimum (ignoring NaN)
result = torch.fmin(x, y)
print(result)
The output result is:
tensor([1., 5., 2.])
Other Extensions