PyTorch torch.pinverse Function
Pytorch torch Reference Manual
torch.pinverseis a function in PyTorch used to compute the Moore-Penrose pseudo-inverse of a matrix. It istorch.linalg.pinvan alias of.
Function Definition
torch.pinverse(input, rcond=1e-15)
Parameters:
input(Tensor): Input matrix.rcond(float, optional): Singular value truncation threshold. Defaults to 1e-15.
Return Value:
torch.Tensor: Returns the pseudo-inverse of the matrix.
Usage Example
Example
import torch
# Create a non-square matrix
A = torch.tensor([[1.0, 2.0, 3.0],
[4.0, 5.0, 6.0]], dtype=torch.float64)
# Compute the pseudo-inverse
A_pinv = torch.pinverse(A)
print("Matrix A:")
print(A)
print("nPseudo-inverse A^+:")
print(A_pinv)
# Create a non-square matrix
A = torch.tensor([[1.0, 2.0, 3.0],
[4.0, 5.0, 6.0]], dtype=torch.float64)
# Compute the pseudo-inverse
A_pinv = torch.pinverse(A)
print("Matrix A:")
print(A)
print("nPseudo-inverse A^+:")
print(A_pinv)
The output result is:
矩阵 A:
tensor([[1., 2., 3.],
[4., 5., 6.]], dtype=torch.float64)
伪逆 A^+:
tensor([[-0.9444, 0.4444],
[-0.2778, 0.2778],
[ 0.3889, 0.1111]], dtype=float64)
Other Extensions