PyTorch torch.quantile Function
Pytorch torch Reference Manual
torch.quantileis a function in PyTorch used to return the quantile of a tensor. A quantile is a value that divides data proportionally.
Function Definition
torch.quantile(input, q, dim, keepdim=False)
Usage Examples
Example
import torch
x = torch.tensor([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
# Return the 0.5 quantile (median)
print("0.5 quantile:", torch.quantile(x, 0.5))
# Return multiple quantiles
print("0.25, 0.75 quantiles:", torch.quantile(x, torch.tensor([0.25, 0.75])))
# Quantile along dim=0
y = torch.tensor([[1, 2, 3], [4, 5, 6]])
print("dim=0 0.5 quantile:", torch.quantile(y, 0.5, dim=0))
x = torch.tensor([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
# Return the 0.5 quantile (median)
print("0.5 quantile:", torch.quantile(x, 0.5))
# Return multiple quantiles
print("0.25, 0.75 quantiles:", torch.quantile(x, torch.tensor([0.25, 0.75])))
# Quantile along dim=0
y = torch.tensor([[1, 2, 3], [4, 5, 6]])
print("dim=0 0.5 quantile:", torch.quantile(y, 0.5, dim=0))
The output result is:
0.5 分位数: tensor(5.5000) 0.25, 0.75 分位数: tensor([2.7500, 7.7500]) dim=0 0.5 分位数: tensor([2.5000, 3.5000, 4.5000])
Other Extensions