# Neural Network Signal Processing on Torch
[](https://badge.fury.io/py/nnspt)
[](https://pepy.tech/project/nnspt?versions=0.0.*)
NNSPT is a Python library for neural network signal processing on PyTorch.
## Table of contents
- [Authors](#authors)
- [Installation](#installation)
- [A simple example](#a-simple-example)
- [Available components](#available-components)
- [Citing](#citing)
## Authors
[**Rostislav Epifanov** — Researcher in Novosibirsk]()
## Installation
Installation from PyPI:
```
pip install nnspt
```
Installation from GitHub:
```
pip install git+https://github.com/rostepifanov/nnspt
```
## A simple example
```python
from nnspt.segmentation.unet import Unet
model = Unet(encoder='tv-resnet34')
```
## Available components
#### Encoders
* <details> <summary>ResNet</summary>
- tv-resnet18
- tv-resnet34
- tv-resnet50
- tv-resnet101
- tv-resnet152
</details>
* <details> <summary>ResNeXt</summary>
- tv-resnext50_32x4d
- tv-resnext101_32x4d
- tv-resnext101_32x8d
- tv-resnext101_32x16d
- tv-resnext101_32x32d
- tv-resnext101_32x48d
</details>
* <details> <summary>DenseNet</summary>
- tv-densenet121
- tv-densenet169
- tv-densenet201
- tv-densenet161
</details>
* <details> <summary>EfficientNetV1</summary>
- timm-efficientnet-b0
- timm-efficientnet-b1
- timm-efficientnet-b2
- timm-efficientnet-b3
- timm-efficientnet-b4
- timm-efficientnet-b5
- timm-efficientnet-b6
- timm-efficientnet-b7
</details>
* <details> <summary>EfficientNetLite</summary>
- timm-efficientnet-lite0
- timm-efficientnet-lite1
- timm-efficientnet-lite2
- timm-efficientnet-lite3
- timm-efficientnet-lite4
</details>
#### Pretraining
* Autoencoder
#### Segmentation
* Unet [[paper](https://arxiv.org/abs/1505.04597)]
## Citing
If you find this library useful for your research, please consider citing:
```
@misc{epifanov2023ecgmentations,
Author = {Rostislav Epifanov},
Title = {NNSTP},
Year = {2023},
Publisher = {GitHub},
Journal = {GitHub repository},
Howpublished = {\url{https://github.com/rostepifanov/nnspt}}
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/rostepifanov/nnspt",
"name": "nnspt",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "",
"author": "Rostislav Epifanov",
"author_email": "rostepifanov@gmail.com",
"download_url": "",
"platform": null,
"description": "# Neural Network Signal Processing on Torch\n\n\n[](https://badge.fury.io/py/nnspt)\n[](https://pepy.tech/project/nnspt?versions=0.0.*)\n\nNNSPT is a Python library for neural network signal processing on PyTorch.\n\n## Table of contents\n- [Authors](#authors)\n- [Installation](#installation)\n- [A simple example](#a-simple-example)\n- [Available components](#available-components)\n- [Citing](#citing)\n\n## Authors\n[**Rostislav Epifanov** \u2014 Researcher in Novosibirsk]()\n\n## Installation\nInstallation from PyPI:\n\n```\npip install nnspt\n```\n\nInstallation from GitHub:\n\n```\npip install git+https://github.com/rostepifanov/nnspt\n```\n\n## A simple example\n```python\nfrom nnspt.segmentation.unet import Unet\n\nmodel = Unet(encoder='tv-resnet34')\n```\n\n## Available components\n#### Encoders\n\n * <details> <summary>ResNet</summary>\n\n - tv-resnet18\n - tv-resnet34\n - tv-resnet50\n - tv-resnet101\n - tv-resnet152\n </details>\n\n * <details> <summary>ResNeXt</summary>\n\n - tv-resnext50_32x4d\n - tv-resnext101_32x4d\n - tv-resnext101_32x8d\n - tv-resnext101_32x16d\n - tv-resnext101_32x32d\n - tv-resnext101_32x48d\n </details>\n\n * <details> <summary>DenseNet</summary>\n\n - tv-densenet121\n - tv-densenet169\n - tv-densenet201\n - tv-densenet161\n\n </details>\n\n * <details> <summary>EfficientNetV1</summary>\n\n - timm-efficientnet-b0\n - timm-efficientnet-b1\n - timm-efficientnet-b2\n - timm-efficientnet-b3\n - timm-efficientnet-b4\n - timm-efficientnet-b5\n - timm-efficientnet-b6\n - timm-efficientnet-b7\n\n </details>\n\n * <details> <summary>EfficientNetLite</summary>\n\n - timm-efficientnet-lite0\n - timm-efficientnet-lite1\n - timm-efficientnet-lite2\n - timm-efficientnet-lite3\n - timm-efficientnet-lite4\n\n </details>\n\n#### Pretraining\n\n * Autoencoder\n\n#### Segmentation\n\n * Unet [[paper](https://arxiv.org/abs/1505.04597)]\n\n## Citing\n\nIf you find this library useful for your research, please consider citing:\n\n```\n@misc{epifanov2023ecgmentations,\n Author = {Rostislav Epifanov},\n Title = {NNSTP},\n Year = {2023},\n Publisher = {GitHub},\n Journal = {GitHub repository},\n Howpublished = {\\url{https://github.com/rostepifanov/nnspt}}\n}\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "",
"version": "0.0.1",
"project_urls": {
"Homepage": "https://github.com/rostepifanov/nnspt"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "cafd5b91618e1ea1ee902d517240134c916c06c55fa018d2917746678e8fbffb",
"md5": "eb8c0265db71bb64bed295419babbb5c",
"sha256": "71dc45c1d1093e52838653a022aaf260a1b9d240ae7e33bd2421683d5571346f"
},
"downloads": -1,
"filename": "nnspt-0.0.1-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "eb8c0265db71bb64bed295419babbb5c",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.7",
"size": 22892,
"upload_time": "2024-01-09T17:29:15",
"upload_time_iso_8601": "2024-01-09T17:29:15.802201Z",
"url": "https://files.pythonhosted.org/packages/ca/fd/5b91618e1ea1ee902d517240134c916c06c55fa018d2917746678e8fbffb/nnspt-0.0.1-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-09 17:29:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "rostepifanov",
"github_project": "nnspt",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "nnspt"
}
JSON
