| Name | samv2 JSON |
| Version |
0.0.4
JSON |
| download |
| home_page | None |
| Summary | fork of the official SAMv2 implementation with cpu support |
| upload_time | 2024-08-04 14:53:52 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | None |
| keywords |
deep-learning
pytorch
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<a href="https://colab.research.google.com/github/SauravMaheshkar/samv2/blob/main/examples/notebooks/samv2_prompted_segmentation_with_wandb_tables.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
[](https://github.com/SauravMaheshkar/samv2/actions/workflows/ci.yml)
CPU **compatible** fork of the official SAMv2 implementation.
## Features 🚀
* CPU compatible
* ships with config files
* Run image and video inference on CPUs
* [Example notebooks](../examples/notebooks/) showcasing inference using weights and biases.
## Installation
You can download it from [pypi](https://pypi.org/) using `pip` as follows:
```bash
pip install samv2
```
or from the repository:
```bash
pip install git+https://github.com/SauravMaheshkar/samv2.git
```
## Usage
After downloading the official weights, you can use the `load_model()` helper method to instantiate a model.
```python
from sam2 import load_model
model = load_model(
variant="tiny",
ckpt_path="artifacts/sam2_hiera_tiny.pt",
device="cpu"
)
```
* [](https://colab.research.google.com/github/SauravMaheshkar/samv2/blob/main/examples/notebooks/samv2_prompted_segmentation_with_wandb_tables.ipynb) Example Notebook to run prompted segmentation on images logging predictions as W&B Tables.
* [](https://colab.research.google.com/github/SauravMaheshkar/samv2/blob/main/examples/notebooks/samv2_automatic_segmentation_with_wandb_tables.ipynb) Example Notebook to run automatic segmentation on images logging predictions as W&B Tables.
## Citation
```bibtex
@article{ravi2024sam2,
title={SAM 2: Segment Anything in Images and Videos},
author={Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and R{\"a}dle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Doll{\'a}r, Piotr and Feichtenhofer, Christoph},
journal={arXiv preprint},
year={2024}
}
```
Raw data
{
"_id": null,
"home_page": null,
"name": "samv2",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "deep-learning, pytorch",
"author": null,
"author_email": "Saurav Maheshkar <sauravvmaheshkar@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/68/d4/e6a7b4f5e22e4b2e17644e9612a30549dfda5e54ca9c626de7348dce7ada/samv2-0.0.4.tar.gz",
"platform": null,
"description": "<a href=\"https://colab.research.google.com/github/SauravMaheshkar/samv2/blob/main/examples/notebooks/samv2_prompted_segmentation_with_wandb_tables.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n[](https://github.com/SauravMaheshkar/samv2/actions/workflows/ci.yml)\n\nCPU **compatible** fork of the official SAMv2 implementation.\n\n## Features \ud83d\ude80\n\n* CPU compatible\n* ships with config files\n* Run image and video inference on CPUs\n* [Example notebooks](../examples/notebooks/) showcasing inference using weights and biases.\n\n## Installation\n\nYou can download it from [pypi](https://pypi.org/) using `pip` as follows:\n\n```bash\npip install samv2\n```\n\nor from the repository:\n\n```bash\npip install git+https://github.com/SauravMaheshkar/samv2.git\n```\n\n## Usage\n\nAfter downloading the official weights, you can use the `load_model()` helper method to instantiate a model.\n\n```python\nfrom sam2 import load_model\n\nmodel = load_model(\n variant=\"tiny\",\n ckpt_path=\"artifacts/sam2_hiera_tiny.pt\",\n device=\"cpu\"\n)\n```\n\n* [](https://colab.research.google.com/github/SauravMaheshkar/samv2/blob/main/examples/notebooks/samv2_prompted_segmentation_with_wandb_tables.ipynb) Example Notebook to run prompted segmentation on images logging predictions as W&B Tables.\n* [](https://colab.research.google.com/github/SauravMaheshkar/samv2/blob/main/examples/notebooks/samv2_automatic_segmentation_with_wandb_tables.ipynb) Example Notebook to run automatic segmentation on images logging predictions as W&B Tables.\n\n## Citation\n\n```bibtex\n@article{ravi2024sam2,\n title={SAM 2: Segment Anything in Images and Videos},\n author={Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and R{\\\"a}dle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Doll{\\'a}r, Piotr and Feichtenhofer, Christoph},\n journal={arXiv preprint},\n year={2024}\n}\n```\n\n",
"bugtrack_url": null,
"license": null,
"summary": "fork of the official SAMv2 implementation with cpu support",
"version": "0.0.4",
"project_urls": {
"homepage": "https://github.com/SauravMaheshkar/samv2",
"repository": "https://github.com/SauravMaheshkar/samv2"
},
"split_keywords": [
"deep-learning",
" pytorch"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fb348717081299a56d169c567bc14197d1294e3fccea303159e86e0a2bfaa1cf",
"md5": "447169d8a2c2827027b308934a454410",
"sha256": "62978465118431c7e4b3509787b5f97fd1d6dd388afbac2056f24721fa056e27"
},
"downloads": -1,
"filename": "samv2-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "447169d8a2c2827027b308934a454410",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 73648,
"upload_time": "2024-08-04T14:53:50",
"upload_time_iso_8601": "2024-08-04T14:53:50.569708Z",
"url": "https://files.pythonhosted.org/packages/fb/34/8717081299a56d169c567bc14197d1294e3fccea303159e86e0a2bfaa1cf/samv2-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "68d4e6a7b4f5e22e4b2e17644e9612a30549dfda5e54ca9c626de7348dce7ada",
"md5": "408840fafc684596a08f1059c8273c05",
"sha256": "2e7fce4b93e45db02485ee41f8a0853e1b9ddf4ecfb474c2f32b8fdbfd7cd543"
},
"downloads": -1,
"filename": "samv2-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "408840fafc684596a08f1059c8273c05",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 58950,
"upload_time": "2024-08-04T14:53:52",
"upload_time_iso_8601": "2024-08-04T14:53:52.157336Z",
"url": "https://files.pythonhosted.org/packages/68/d4/e6a7b4f5e22e4b2e17644e9612a30549dfda5e54ca9c626de7348dce7ada/samv2-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-04 14:53:52",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "SauravMaheshkar",
"github_project": "samv2",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "samv2"
}
