Data

Tools

Indexes

Applications

Experiments

Open Source Science

torch.nn.cubichermiteinterpolation

CubicHermite interpolators written in PyTorch. These funcitons inherit nn.Module, are autograd-compatible, CUDA-compatible, and can be seamlessly incorporated in neural networks.

https://github.com/johnlamaster/torch.nn.cubichermiteinterpolation

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.2%) to scientific vocabulary
Last synced: 7 months ago · JSON representation ·

Repository

CubicHermite interpolators written in PyTorch. These funcitons inherit nn.Module, are autograd-compatible, CUDA-compatible, and can be seamlessly incorporated in neural networks.

Basic Info
  • Host: GitHub
  • Owner: JohnLaMaster
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 37.1 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 1
  • Releases: 1
Created almost 4 years ago · Last pushed almost 3 years ago
Metadata Files
Readme License Citation

README.md

torch.nn.CubicHermiteInterpolation

CubicHermite interpolators written in PyTorch. These funcitons inherit nn.Module, are autograd-compatible, and can run inside neural networks on GPUs.

The original dimensions must be specified for every axis when defining the interpolator module. The desired dimensions are required inputs to the chinterp.interp() function call. This allows the interpolator to resample, crop, and interpolate with both uniform and non-uniform sampling schemes.

Multi-dimensional data is interpolated one dimension at a time starting with the last dimension and moving inward. The dimensionality of the interpolator refers to the dimensionality of the data. CubicHermiteSplines1d accepts n-dimensional input data but will only interpolate along dim=-1.

Currently, this family of interpolators is based on cubic Hermite interpolation and includes: splines, akima, and modified akima. There are implementations for 1D, 2D, 3D, and 4D data.

If you have ideas, questions, or contributions, please post in the issues section.

If this repository is useful for your work, please cite this repo to improve visibility.

Owner

  • Name: John LaMaster
  • Login: JohnLaMaster
  • Kind: user
  • Location: Munich, Germany
  • Company: Technical Univeristy Munich

I am a Biomedical Engineer currently working on my doctorate in Medical Imaging-Data Analysis using Deep Learning.

Citation (CITATION.cff) 

cff-version: 1.0.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "LaMaster"
  given-names: "John T"
  orcid: "https://orcid.org/0000-0002-2149-771X"
title: "torch.nn.CubicHermiteInterpolation"
version: 1.0.0
doi: 10.5281/zenodo.6573020
date-released: 2022-05-23
url: "https://github.com/JohnLaMaster/torch.nn.CubicHermiteInterpolation"

GitHub Events

Total
Last Year