Thin Plate Spline implementation with PyTorch
Project description
torch-tps
Implementation of Thin Plate Spline. (See numpy implementation with thin-plate-spline library)
Install
Pip
$ pip install torch-tps
Conda
Not yet available
Getting started
import torch
from tps import ThinPlateSpline
# Some data
X_c = torch.normal(0, 1, (800, 3))
X_t = torch.normal(0, 2, (800, 2))
X = torch.normal(0, 1, (300, 3))
# Create the tps object
tps = ThinPlateSpline(alpha=0.0) # 0 Regularization
# Fit the control and target points
tps.fit(X_c, X_t)
# Transform new points
Y = tps.transform(X)
Also have a look at example.py
Build and Deploy
$ python -m build
$ python -m twine upload dist/*
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torch-tps-1.1.0.tar.gz
(4.5 kB
view hashes)
Built Distribution
Close
Hashes for torch_tps-1.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e614b74438691bc9988886b175bedb66faca9ab06ba2c8c8294944f3e57ad3fa |
|
MD5 | 28180c994edb15c6d389ee172168c37b |
|
BLAKE2b-256 | 234e9002185606d8ecccc637cc25e7b63df03788d6da4eed748820f9cd6b717c |