PyTorch torch.mode Function
Pytorch torch Reference Manual
torch.modeIt is a function in PyTorch used to return the mode of a tensor. The mode is the value that appears most frequently in a set of data.
Function Definition
torch.mode(input, dim, keepdim=False)
Usage Example
Example
import torch
x = torch.tensor([1, 2, 2, 3, 3, 3])
# Return the mode
print("Mode:", torch.mode(x))
# Mode along dim=0
y = torch.tensor([[1, 2, 2], [1, 2, 3]])
print("dim=0 mode:", torch.mode(y, dim=0))
# Mode along dim=1
print("dim=1 mode:", torch.mode(y, dim=1))
x = torch.tensor([1, 2, 2, 3, 3, 3])
# Return the mode
print("Mode:", torch.mode(x))
# Mode along dim=0
y = torch.tensor([[1, 2, 2], [1, 2, 3]])
print("dim=0 mode:", torch.mode(y, dim=0))
# Mode along dim=1
print("dim=1 mode:", torch.mode(y, dim=1))
The output result is:
众数: torch.return_types.mode(values=tensor(3), indices=tensor(4)) dim=0 众数: torch.return_types.mode(values=tensor([1, 2, 2]), indices=tensor([0, 0, 0])) dim=1 众数: torch.return_types.mode(values=tensor([2, 3]), indices=tensor([1, 2]))
Other Extensions