Skip to main content

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

$ pip install build twine
$ 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-1.0.0.tar.gz (4.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

torch_tps-1.0.0-py3-none-any.whl (4.7 kB view details)

Uploaded Python 3

File details

Details for the file torch-tps-1.0.0.tar.gz.

File metadata

  • Download URL: torch-tps-1.0.0.tar.gz
  • Upload date:
  • Size: 4.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.8.13

File hashes

Hashes for torch-tps-1.0.0.tar.gz
Algorithm Hash digest
SHA256 956134b579fcf10323821828dbc3198694ec46b81c08234009a307ea984d9804
MD5 e89c2a146d12e510102a4803490f63db
BLAKE2b-256 39e6df77096260917518ac56ea5b340d8f59bdda740b535f37d6c6047ab3c512

See more details on using hashes here.

File details

Details for the file torch_tps-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: torch_tps-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 4.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.8.13

File hashes

Hashes for torch_tps-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d2ec99a25409b8eac73c55c9291b1065cb53f05265ce8f025b2f890f49a54674
MD5 5d100de7387ab343f8cc3ae15192f01b
BLAKE2b-256 589568dfa4173eb05eaccd0c2ccf731e3dfba2809c4192f5cc6d9b1663229d25

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page