# torch_contour
<figure>
<p align="center">
<img
src="vary_nodes.jpg"
alt="Example of torch contour on a circle when varying the number of nodes"
width="500">
<figcaption>Example of torch contour on a circle when varying the number of nodes</figcaption>
</p>
</figure>
This library contains 2 pytorch layers for performing the diferentiable operations of :
1. contour to mask
2. contour to distance map.
It can therefore be used to transform a polygon into a binary mask or distance map in a completely differentiable way.
In particular, it can be used to transform the detection task into a segmentation task.
The two layers have no learnable weight, so all it does is apply a function in a derivative way.
## Input (Float):
A polygon of size $2 \times n$ with \
with $n$ the number of nodes
## Output (Float):
A mask or distance map of size $1 \times H \times W$.\
with $H$ and $W$ respectively the Heigh and Width of the distance map or mask.
## Important:
The polygon must have values between 0 and 1. It is therefore important to apply a sigmoid function before the layer.*.
## Example:
```
from torch_contour.torch_contour import Contour_to_distance_map, Contour_to_mask
import torch
import matplotlib.pyplot as plt
x = torch.tensor([[0.1,0.1],
[0.1,0.9],
[0.9,0.9],
[0.9,0.1]])[None]
Dmap = Contour_to_distance_map(200)
Mask = Contour_to_mask(200)
plt.imshow(Dmap(x).cpu().detach().numpy()[0,0])
plt.show()
plt.imshow(Mask(x).cpu().detach().numpy()[0,0])
plt.show()
```
Raw data
{
"_id": null,
"home_page": "https://github.com/antoinehabis/torch_contour",
"name": "torch-contour",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "differentiable contour processing, pytorch, machine learning",
"author": "Antoine Habis",
"author_email": "antoine.habis.tlcm@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/1c/15/d62b4908e6521b3ec36f63dd46d20f10755410f9c1964be30ee5b8642e43/torch_contour-1.0.0.tar.gz",
"platform": null,
"description": "# torch_contour\n<figure>\n<p align=\"center\">\n <img \n src=\"vary_nodes.jpg\"\n alt=\"Example of torch contour on a circle when varying the number of nodes\"\n width=\"500\">\n <figcaption>Example of torch contour on a circle when varying the number of nodes</figcaption>\n</p>\n</figure>\n\nThis library contains 2 pytorch layers for performing the diferentiable operations of :\n\n1. contour to mask\n2. contour to distance map. \n\nIt can therefore be used to transform a polygon into a binary mask or distance map in a completely differentiable way.\nIn particular, it can be used to transform the detection task into a segmentation task.\nThe two layers have no learnable weight, so all it does is apply a function in a derivative way.\n\n\n\n## Input (Float):\n\nA polygon of size $2 \\times n$ with \\\nwith $n$ the number of nodes\n\n\n## Output (Float):\n\nA mask or distance map of size $1 \\times H \\times W$.\\\nwith $H$ and $W$ respectively the Heigh and Width of the distance map or mask.\n\n## Important: \n\nThe polygon must have values between 0 and 1. It is therefore important to apply a sigmoid function before the layer.*.\n\n## Example:\n\n ```\nfrom torch_contour.torch_contour import Contour_to_distance_map, Contour_to_mask\nimport torch\nimport matplotlib.pyplot as plt\n\nx = torch.tensor([[0.1,0.1],\n [0.1,0.9],\n [0.9,0.9],\n [0.9,0.1]])[None]\n\nDmap = Contour_to_distance_map(200)\nMask = Contour_to_mask(200)\n\nplt.imshow(Dmap(x).cpu().detach().numpy()[0,0])\nplt.show()\nplt.imshow(Mask(x).cpu().detach().numpy()[0,0])\nplt.show()\n```\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Differentiable contour to mask and contour to distance map implementation with PyTorch",
"version": "1.0.0",
"project_urls": {
"Homepage": "https://github.com/antoinehabis/torch_contour"
},
"split_keywords": [
"differentiable contour processing",
" pytorch",
" machine learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "76aa5fc4012094c5d4014cbeefde0b9c8c4c12d55cff90470db73f761ca5e10c",
"md5": "cf9cbb0a911a4a989cda1aa6945a7c64",
"sha256": "c83f4e72d333dc78299a2cf3bfe48fcb021a18f6f5b593e9bfd3776ebdef9fc7"
},
"downloads": -1,
"filename": "torch_contour-1.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "cf9cbb0a911a4a989cda1aa6945a7c64",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 4539,
"upload_time": "2024-05-17T14:35:03",
"upload_time_iso_8601": "2024-05-17T14:35:03.694151Z",
"url": "https://files.pythonhosted.org/packages/76/aa/5fc4012094c5d4014cbeefde0b9c8c4c12d55cff90470db73f761ca5e10c/torch_contour-1.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "1c15d62b4908e6521b3ec36f63dd46d20f10755410f9c1964be30ee5b8642e43",
"md5": "fe789762ba1e73780d965bd24d789d9e",
"sha256": "396596547374fee2d3ccc1c82d978e24e1143f5b514920c51040e0d6d0bae4ca"
},
"downloads": -1,
"filename": "torch_contour-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "fe789762ba1e73780d965bd24d789d9e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 4150,
"upload_time": "2024-05-17T14:35:05",
"upload_time_iso_8601": "2024-05-17T14:35:05.371477Z",
"url": "https://files.pythonhosted.org/packages/1c/15/d62b4908e6521b3ec36f63dd46d20f10755410f9c1964be30ee5b8642e43/torch_contour-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-17 14:35:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "antoinehabis",
"github_project": "torch_contour",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "torch-contour"
}
JSON
