# torch-tps
[](https://github.com/raphaelreme/torch-tps/actions/workflows/tests.yml)
Implementation of Thin Plate Spline.
(See numpy implementation with [thin-plate-spline](https://github.com/raphaelreme/tps) library)
## Install
### Pip
```bash
$ pip install torch-tps
```
### Conda
Not yet available
## Getting started
```python
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)
```
## Examples
We provide different examples in the `example` folder. (From interpolation, to multidimensional cases and image warping).
### Image warping
The elastic deformation of TPS can be used for image warping. Here is an example of tps to increase/decrease the size of the center of the image or using random control points:
Have a look at `example/image_warping.py`.
## Build and Deploy
```bash
$ python -m build
$ python -m twine upload dist/*
```
Raw data
{
"_id": null,
"home_page": "https://github.com/raphaelreme/torch-tps",
"name": "torch-tps",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "interpolation, pytorch, machine learning",
"author": "Raphael Reme",
"author_email": "raphaelreme-dev@protonmail.com",
"download_url": "https://files.pythonhosted.org/packages/63/4c/c042b7b0c6e4c66626a945b2d734dd27be82401e800019899bcaa06d04a3/torch_tps-1.1.1.tar.gz",
"platform": null,
"description": "# torch-tps\n\n[](https://github.com/raphaelreme/torch-tps/actions/workflows/tests.yml)\n\nImplementation of Thin Plate Spline.\n(See numpy implementation with [thin-plate-spline](https://github.com/raphaelreme/tps) library)\n\n\n## Install\n\n### Pip\n\n```bash\n$ pip install torch-tps\n```\n\n### Conda\n\nNot yet available\n\n\n## Getting started\n\n```python\n\nimport torch\nfrom tps import ThinPlateSpline\n\n# Some data\nX_c = torch.normal(0, 1, (800, 3))\nX_t = torch.normal(0, 2, (800, 2))\nX = torch.normal(0, 1, (300, 3))\n\n# Create the tps object\ntps = ThinPlateSpline(alpha=0.0) # 0 Regularization\n\n# Fit the control and target points\ntps.fit(X_c, X_t)\n\n# Transform new points\nY = tps.transform(X)\n```\n\n## Examples\n\nWe provide different examples in the `example` folder. (From interpolation, to multidimensional cases and image warping).\n\n\n### Image warping\n\nThe elastic deformation of TPS can be used for image warping. Here is an example of tps to increase/decrease the size of the center of the image or using random control points:\n\n\n\nHave a look at `example/image_warping.py`.\n\n## Build and Deploy\n\n```bash\n$ python -m build\n$ python -m twine upload dist/*\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Thin Plate Spline implementation with PyTorch",
"version": "1.1.1",
"project_urls": {
"Homepage": "https://github.com/raphaelreme/torch-tps"
},
"split_keywords": [
"interpolation",
" pytorch",
" machine learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a0fb4063b8b6c3ded06c7d4e613752527b08c4bbfb21107f5b0749cc6b2d1ddf",
"md5": "1b8d6876830d19bbb48adac635de3d6a",
"sha256": "d0a6590a7e762721baa031a973c9f9345de16334c32e3158e78c78853568c2b0"
},
"downloads": -1,
"filename": "torch_tps-1.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1b8d6876830d19bbb48adac635de3d6a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 5123,
"upload_time": "2024-04-26T09:19:33",
"upload_time_iso_8601": "2024-04-26T09:19:33.352316Z",
"url": "https://files.pythonhosted.org/packages/a0/fb/4063b8b6c3ded06c7d4e613752527b08c4bbfb21107f5b0749cc6b2d1ddf/torch_tps-1.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "634cc042b7b0c6e4c66626a945b2d734dd27be82401e800019899bcaa06d04a3",
"md5": "b53e6a778aa8007a52a1a72406594b8d",
"sha256": "3f56699b6dc933b57b11e8ca59fe6165a052f818dff37867b1c88ce2b49437a4"
},
"downloads": -1,
"filename": "torch_tps-1.1.1.tar.gz",
"has_sig": false,
"md5_digest": "b53e6a778aa8007a52a1a72406594b8d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 4796,
"upload_time": "2024-04-26T09:19:34",
"upload_time_iso_8601": "2024-04-26T09:19:34.859263Z",
"url": "https://files.pythonhosted.org/packages/63/4c/c042b7b0c6e4c66626a945b2d734dd27be82401e800019899bcaa06d04a3/torch_tps-1.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-26 09:19:34",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "raphaelreme",
"github_project": "torch-tps",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "torch-tps"
}
JSON
