[](https://www.python.org/) [](https://badge.fury.io/py/keras-vision) [](https://github.com/keras-team/keras/releases) 
Porting all models from everywhere to Keras to leverage multi-backend support.
Cause why not?🤷🏻♂️
# Table of Contents
- [Table of Contents](#table-of-contents)
- [Progress](#progress)
- [Updates](#updates)
- [Quick Setup](#quick-setup)
- [Stable PyPi Package](#stable-pypi-package)
- [OR](#or)
- [Latest Git Updates](#latest-git-updates)
- [Models Supported](#models-supported)
## Progress
- Working on adding MobileNet V4
## Updates
1. [2024-06-24] Released MobileViT v2 - All Image Classification variants.
2. [2024-05-15] Fixed MobileViT v1 - Now works will all 3 backends. 🎉🎉
3. [2024-05-04] Converted MobileViT to Keras 3 and released weights of all 3 variants.
1. Jax backend currently not working, I'm working on a fix.
2. Release: <https://github.com/veb-101/keras-vision/releases/tag/v0.4>
## Quick Setup
### Stable PyPi Package
```bash
pip install -U keras-vision
```
### OR
### Latest Git Updates
```bash
pip install git+https://github.com/veb-101/keras-vision.git
```
## Models Supported
<table>
<thead>
<tr>
<th style="text-align:center">
<strong># No.</strong>
</th>
<th style="text-align:center">
<strong>Models</strong>
</th>
<th style="text-align:center">
<strong>Paper</strong>
</th>
<th style="text-align:center">
<strong>Additional Materials</strong>
</th>
<th style="text-align:center">
<strong>Example notebook</strong>
</th>
<th style="text-align:center">
<strong>Weights URL</strong>
</th>
</tr>
</thead>
<tbody>
<tr>
<td style="text-align:center">1</td>
<td style="text-align:center">
<a href="https://github.com/veb-101/keras-vision/blob/main/keras_vision/MobileViT_v1/mobile_vit_v1.py">MobileViT-V1</a>
</td>
<td style="text-align:center">
<a href="https://arxiv.org/abs/2110.02178">MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer</a>
</td>
<td style="text-align:center">
<a href="https://learnopencv.com/mobilevit-keras-3/">Blogpost: Building MobileViT In Keras 3</a>
</td>
<td style="text-align:center">
<a href="https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/mobile_vit_v1.ipynb">Colab link</a>
</td>
<td style="text-align:center">
<a href="https://github.com/veb-101/keras-vision/releases/tag/v0.4">Releases v0.4</a>
</td>
<tr>
<td style="text-align:center">1</td>
<td style="text-align:center">
<a href="https://github.com/veb-101/keras-vision/blob/main/keras_vision/MobileViT_v2/mobile_vit_v2.py">MobileViT-V2</a>
</td>
<td style="text-align:center">
<a href="https://arxiv.org/abs/2206.02680">Separable Self-attention for Mobile Vision Transformers</a>
</td>
<td style="text-align:center">
--
</td>
<td style="text-align:center">
<a href="https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/mobile_vit_v2.ipynb">Colab link</a>
</td>
<td style="text-align:center">
<a href="https://github.com/veb-101/keras-vision/releases/tag/v0.5">Releases v0.5</a>
</td>
</tr>
</tbody>
</table>
Raw data
{
"_id": null,
"home_page": null,
"name": "keras-vision",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "keras3, tensorflow, Jax, PyTorch, Vision",
"author": null,
"author_email": "Vaibhav Singh <vaibhav.singh.3001@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/44/59/15eedeb2b4655b84d987c3161bdbf12535f0466db6cb8de10eff754fe6a6/keras_vision-0.5.0.tar.gz",
"platform": null,
"description": "[](https://www.python.org/) [](https://badge.fury.io/py/keras-vision) [](https://github.com/keras-team/keras/releases) \r\n\r\nPorting all models from everywhere to Keras to leverage multi-backend support.\r\n\r\nCause why not?\ud83e\udd37\ud83c\udffb\u200d\u2642\ufe0f\r\n\r\n# Table of Contents\r\n\r\n- [Table of Contents](#table-of-contents)\r\n - [Progress](#progress)\r\n - [Updates](#updates)\r\n - [Quick Setup](#quick-setup)\r\n - [Stable PyPi Package](#stable-pypi-package)\r\n - [OR](#or)\r\n - [Latest Git Updates](#latest-git-updates)\r\n - [Models Supported](#models-supported)\r\n\r\n## Progress\r\n\r\n- Working on adding MobileNet V4\r\n\r\n## Updates\r\n\r\n1. [2024-06-24] Released MobileViT v2 - All Image Classification variants.\r\n2. [2024-05-15] Fixed MobileViT v1 - Now works will all 3 backends. \ud83c\udf89\ud83c\udf89\r\n3. [2024-05-04] Converted MobileViT to Keras 3 and released weights of all 3 variants.\r\n 1. Jax backend currently not working, I'm working on a fix.\r\n 2. Release: <https://github.com/veb-101/keras-vision/releases/tag/v0.4>\r\n\r\n## Quick Setup\r\n\r\n### Stable PyPi Package\r\n\r\n```bash\r\npip install -U keras-vision\r\n```\r\n\r\n### OR\r\n\r\n### Latest Git Updates\r\n\r\n```bash\r\npip install git+https://github.com/veb-101/keras-vision.git\r\n```\r\n\r\n## Models Supported\r\n\r\n<table>\r\n <thead>\r\n <tr>\r\n <th style=\"text-align:center\">\r\n <strong># No.</strong>\r\n </th>\r\n <th style=\"text-align:center\">\r\n <strong>Models</strong>\r\n </th>\r\n <th style=\"text-align:center\">\r\n <strong>Paper</strong>\r\n </th>\r\n <th style=\"text-align:center\">\r\n <strong>Additional Materials</strong>\r\n </th>\r\n <th style=\"text-align:center\">\r\n <strong>Example notebook</strong>\r\n </th>\r\n <th style=\"text-align:center\">\r\n <strong>Weights URL</strong>\r\n </th>\r\n </tr>\r\n </thead>\r\n <tbody>\r\n <tr>\r\n <td style=\"text-align:center\">1</td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://github.com/veb-101/keras-vision/blob/main/keras_vision/MobileViT_v1/mobile_vit_v1.py\">MobileViT-V1</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://arxiv.org/abs/2110.02178\">MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://learnopencv.com/mobilevit-keras-3/\">Blogpost: Building MobileViT In Keras 3</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/mobile_vit_v1.ipynb\">Colab link</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://github.com/veb-101/keras-vision/releases/tag/v0.4\">Releases v0.4</a>\r\n </td>\r\n <tr>\r\n <td style=\"text-align:center\">1</td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://github.com/veb-101/keras-vision/blob/main/keras_vision/MobileViT_v2/mobile_vit_v2.py\">MobileViT-V2</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://arxiv.org/abs/2206.02680\">Separable Self-attention for Mobile Vision Transformers</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n --\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://colab.research.google.com/github/veb-101/keras-vision/blob/main/examples/mobile_vit_v2.ipynb\">Colab link</a>\r\n </td>\r\n <td style=\"text-align:center\">\r\n <a href=\"https://github.com/veb-101/keras-vision/releases/tag/v0.5\">Releases v0.5</a>\r\n </td>\r\n </tr>\r\n </tbody>\r\n</table>\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Building Vision models in Keras3 for framework-agnostic training and inference.",
"version": "0.5.0",
"project_urls": {
"Homepage": "https://github.com/veb-101/keras-vision"
},
"split_keywords": [
"keras3",
" tensorflow",
" jax",
" pytorch",
" vision"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ca0e1dacda07434ad77d51dca823b8e4e374e7e36aedb9a7f6ea34e6b534a302",
"md5": "e358136b1de17110f688b62ce20adcd4",
"sha256": "487f14b4f329ced114ef002d6b24833fc5c6467241541ba030f0419e3c2975ed"
},
"downloads": -1,
"filename": "keras_vision-0.5.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e358136b1de17110f688b62ce20adcd4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 21720,
"upload_time": "2024-06-23T20:33:55",
"upload_time_iso_8601": "2024-06-23T20:33:55.645286Z",
"url": "https://files.pythonhosted.org/packages/ca/0e/1dacda07434ad77d51dca823b8e4e374e7e36aedb9a7f6ea34e6b534a302/keras_vision-0.5.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "445915eedeb2b4655b84d987c3161bdbf12535f0466db6cb8de10eff754fe6a6",
"md5": "8408837f2ac7f87e117fc001dc734a01",
"sha256": "40e7e2c6702bd06d2d7f645495d7ada0e4646a6241cc2f2ad80ee01adb1c45a4"
},
"downloads": -1,
"filename": "keras_vision-0.5.0.tar.gz",
"has_sig": false,
"md5_digest": "8408837f2ac7f87e117fc001dc734a01",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 17892,
"upload_time": "2024-06-23T20:34:00",
"upload_time_iso_8601": "2024-06-23T20:34:00.800825Z",
"url": "https://files.pythonhosted.org/packages/44/59/15eedeb2b4655b84d987c3161bdbf12535f0466db6cb8de10eff754fe6a6/keras_vision-0.5.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-23 20:34:00",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "veb-101",
"github_project": "keras-vision",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "keras",
"specs": []
},
{
"name": "jax",
"specs": []
},
{
"name": "jax",
"specs": []
},
{
"name": "tensorflow",
"specs": []
}
],
"lcname": "keras-vision"
}
JSON
