<p align="center">
<br>
<img src="docs/source/imgs/Group 13.png" width="500"/>
</br>
<br>
<strong> Transmute AI Model Efficiency Toolkit </strong>
</br>
</p>
<p align="center">
<a href="https://github.com/transmuteAI/trailmet/blob/dev/LICENSE">
<img alt="GitHub" src="https://img.shields.io/github/license/transmuteAI/trailmet?color=blue">
</a>
<a href="https://transmuteai-trailmet.readthedocs.io/en/latest/">
<img alt="Documentation" src="https://img.shields.io/badge/docs-passing-brightgreen">
</a>
<a href="https://github.com/transmuteAI/trailmet/actions/workflows/ci.yml">
<img alt="Run tests with pytest" src="https://github.com/transmuteAI/trailmet/actions/workflows/ci.yml/badge.svg">
</a>
<a href="#">
<img alt="GitHub Stars" src="https://img.shields.io/github/stars/transmuteAI/trailmet">
</a>
<a href="#">
<img alt="GitHub Forks" src="https://img.shields.io/github/forks/transmuteAI/trailmet">
</a>
</p>
<h3 align="justified">
<!-- <p>Transmute AI Lab Model Efficiency Toolkit -->
</h3>
# Introduction
Trailmet is a model efficiency toolkit for compressing deep learning models using state of the art compression techniques.
Today deep learning models are not deployable because of their huge memory footprint, TRAILMET is an effort to make deep learning models more efficient in their size to performance ratio. It is developed using Pytorch 1.13.
### Major features
- State of the art compression algorithms implemented.
- Demo notebooks for training each algorithm.
- Modular Design: All alogithms are modular and can customized easily for any kind of model and dataset.
# Installation
Below are quick steps for installation:
```shell
git clone https://github.com/transmuteAI/trailmet.git
cd trailmet
conda create -n trailmet
conda activate trailmet
conda install pytorch=1.13 torchvision=0.14 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install -r requirements.txt
```
# Algorithms Implemented
Demo notebooks for each algorithm is added in [experiments](https://github.com/transmuteAI/trailmet/blob/dev/experiments) folder
<details open>
<summary> Knowledge Distillation</summary>
- [x] [Response KD](https://arxiv.org/abs/1503.02531)
- [x] [Factor Transfer](https://arxiv.org/abs/1802.04977)
- [x] [Attention Transfer](https://arxiv.org/abs/1612.03928)
</details>
<details open>
<summary> Pruning </summary>
- [x] [Chipnet](https://arxiv.org/abs/2102.07156)
- [x] [Network slimming](https://arxiv.org/abs/1708.06519)
- [x] [Growth Regularization](https://arxiv.org/abs/2012.09243)
</details>
<details open>
<summary> Quantization</summary>
- [x] [BitSplit](https://dl.acm.org/doi/abs/10.5555/3524938.3525851)
- [x] [BRECQ](https://arxiv.org/abs/2102.05426)
- [x] [LAPQ](https://arxiv.org/abs/1911.07190)
</details>
<details open>
<summary> Binarization</summary>
- [x] [BiRealNet](https://arxiv.org/abs/1808.00278)
- [x] [ReActNet](https://arxiv.org/abs/2003.03488)
- [x] [BNN-BN](https://arxiv.org/abs/2104.08215v1)
</details>
# Acknowledgement
# Citation
If you find this project useful in your research, please consider cite:
```BibTeX
@misc{,
title={},
author={},
howpublished = {}},
year={2023}
}
```
# License
This project is released under the [MIT license](LICENSE).
Raw data
{
"_id": null,
"home_page": "https://github.com/transmuteAI/trailmet",
"name": "trailmet",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "computer vision,image classification,model efficiency",
"author": "TrAILMET Contributors",
"author_email": "transmute.ai@gmail.com",
"download_url": "",
"platform": null,
"description": "<p align=\"center\">\n <br>\n <img src=\"docs/source/imgs/Group 13.png\" width=\"500\"/>\n </br>\n <br>\n <strong> Transmute AI Model Efficiency Toolkit </strong>\n </br>\n</p>\n<p align=\"center\">\n <a href=\"https://github.com/transmuteAI/trailmet/blob/dev/LICENSE\">\n <img alt=\"GitHub\" src=\"https://img.shields.io/github/license/transmuteAI/trailmet?color=blue\">\n </a>\n <a href=\"https://transmuteai-trailmet.readthedocs.io/en/latest/\">\n <img alt=\"Documentation\" src=\"https://img.shields.io/badge/docs-passing-brightgreen\">\n </a>\n <a href=\"https://github.com/transmuteAI/trailmet/actions/workflows/ci.yml\">\n <img alt=\"Run tests with pytest\" src=\"https://github.com/transmuteAI/trailmet/actions/workflows/ci.yml/badge.svg\">\n </a>\n <a href=\"#\">\n <img alt=\"GitHub Stars\" src=\"https://img.shields.io/github/stars/transmuteAI/trailmet\">\n </a>\n <a href=\"#\">\n <img alt=\"GitHub Forks\" src=\"https://img.shields.io/github/forks/transmuteAI/trailmet\">\n </a>\n</p>\n<h3 align=\"justified\">\n<!-- <p>Transmute AI Lab Model Efficiency Toolkit -->\n</h3>\n\n# Introduction\n\nTrailmet is a model efficiency toolkit for compressing deep learning models using state of the art compression techniques.\nToday deep learning models are not deployable because of their huge memory footprint, TRAILMET is an effort to make deep learning models more efficient in their size to performance ratio. It is developed using Pytorch 1.13.\n\n### Major features\n\n- State of the art compression algorithms implemented.\n- Demo notebooks for training each algorithm.\n- Modular Design: All alogithms are modular and can customized easily for any kind of model and dataset.\n\n# Installation\n\nBelow are quick steps for installation:\n\n```shell\ngit clone https://github.com/transmuteAI/trailmet.git\ncd trailmet\nconda create -n trailmet\nconda activate trailmet\nconda install pytorch=1.13 torchvision=0.14 pytorch-cuda=11.7 -c pytorch -c nvidia\npip install -r requirements.txt\n```\n\n# Algorithms Implemented\n\nDemo notebooks for each algorithm is added in [experiments](https://github.com/transmuteAI/trailmet/blob/dev/experiments) folder\n\n<details open>\n<summary> Knowledge Distillation</summary>\n\n- [x] [Response KD](https://arxiv.org/abs/1503.02531)\n- [x] [Factor Transfer](https://arxiv.org/abs/1802.04977)\n- [x] [Attention Transfer](https://arxiv.org/abs/1612.03928)\n\n</details>\n\n<details open>\n<summary> Pruning </summary>\n\n- [x] [Chipnet](https://arxiv.org/abs/2102.07156)\n- [x] [Network slimming](https://arxiv.org/abs/1708.06519)\n- [x] [Growth Regularization](https://arxiv.org/abs/2012.09243)\n\n</details>\n\n<details open>\n<summary> Quantization</summary>\n\n- [x] [BitSplit](https://dl.acm.org/doi/abs/10.5555/3524938.3525851)\n- [x] [BRECQ](https://arxiv.org/abs/2102.05426)\n- [x] [LAPQ](https://arxiv.org/abs/1911.07190)\n\n</details>\n\n<details open>\n<summary> Binarization</summary>\n\n- [x] [BiRealNet](https://arxiv.org/abs/1808.00278)\n- [x] [ReActNet](https://arxiv.org/abs/2003.03488)\n- [x] [BNN-BN](https://arxiv.org/abs/2104.08215v1)\n\n</details>\n\n# Acknowledgement\n\n# Citation\n\nIf you find this project useful in your research, please consider cite:\n\n```BibTeX\n@misc{,\n title={},\n author={},\n howpublished = {}},\n year={2023}\n}\n```\n\n# License\n\nThis project is released under the [MIT license](LICENSE).\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Transmute AI Model Efficiency Toolkit",
"version": "0.0.1.1",
"project_urls": {
"Homepage": "https://github.com/transmuteAI/trailmet"
},
"split_keywords": [
"computer vision",
"image classification",
"model efficiency"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "bd609879d380befc7500abc2d5bb12254962cf5b51c72f9f23894d8a1105c1d0",
"md5": "f496d4ebf55fd45381b776843a02c1b1",
"sha256": "dad2343ecfb3dbcd46bdd1db5c65c61058d2f9b5895f9df40f9ecbcbcbf67271"
},
"downloads": -1,
"filename": "trailmet-0.0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f496d4ebf55fd45381b776843a02c1b1",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 186607,
"upload_time": "2023-07-02T18:21:14",
"upload_time_iso_8601": "2023-07-02T18:21:14.677449Z",
"url": "https://files.pythonhosted.org/packages/bd/60/9879d380befc7500abc2d5bb12254962cf5b51c72f9f23894d8a1105c1d0/trailmet-0.0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-07-02 18:21:14",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "transmuteAI",
"github_project": "trailmet",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "codecarbon",
"specs": [
[
"==",
"2.2.3"
]
]
},
{
"name": "pandas",
"specs": [
[
"==",
"2.0.2"
]
]
},
{
"name": "tqdm",
"specs": [
[
"==",
"4.65.0"
]
]
},
{
"name": "timm",
"specs": [
[
"==",
"0.9.2"
]
]
},
{
"name": "matplotlib",
"specs": [
[
"==",
"3.7.1"
]
]
},
{
"name": "thop",
"specs": [
[
"==",
"0.1.1.post2209072238"
]
]
},
{
"name": "scipy",
"specs": [
[
"==",
"1.10.1"
]
]
},
{
"name": "gdown",
"specs": [
[
"==",
"4.7.1"
]
]
},
{
"name": "datasets",
"specs": [
[
"==",
"2.13.0"
]
]
},
{
"name": "scikit-learn",
"specs": [
[
"==",
"1.2.2"
]
]
},
{
"name": "pytest",
"specs": [
[
"==",
"7.3.1"
]
]
},
{
"name": "torch_pruning",
"specs": [
[
"==",
"1.1.9"
]
]
},
{
"name": "wandb",
"specs": [
[
"==",
"0.15.4"
]
]
}
],
"lcname": "trailmet"
}
JSON
