<div align="center">
<p>
<a align="center" href="" target="_blank">
<img
width="850"
src="https://media.roboflow.com/open-source/autodistill/autodistill-banner.png"
>
</a>
</p>
</div>
# Autodistill Kosmos-2 Module
This repository contains the code supporting the Kosmos-2 base model for use with [Autodistill](https://github.com/autodistill/autodistill).
[Kosmos-2](https://github.com/microsoft/unilm/tree/master/kosmos-2), developed by Microsoft, is a multimodal language model that you can use for zero-shot object detection. You can use Kosmos-2 with autodistill for object detection.
Read the full [Autodistill documentation](https://autodistill.github.io/autodistill/).
Read the [Kosmos-2 Autodistill documentation](https://autodistill.github.io/autodistill/base_models/kosmos_2/).
## Installation
To use Kosmos-2 with autodistill, you need to install the following dependency:
```bash
pip3 install autodistill-kosmos-2
```
## Quickstart
```python
from autodistill_kosmos_2 import Kosmos2
# define an ontology to map class names to our Kosmos2 prompt
# the ontology dictionary has the format {caption: class}
# where caption is the prompt sent to the base model, and class is the label that will
# be saved for that caption in the generated annotations
# then, load the model
base_model = Kosmos2(
ontology=CaptionOntology(
{
"person": "person",
"a forklift": "forklift"
}
)
)
predictions = base_model.predict("./example.png")
base_model.label("./context_images", extension=".jpeg")
```
## License
This package is implemented using the [Transformers Kosmos-2 implementation](https://huggingface.co/microsoft/kosmos-2-patch14-224). The underlying Kosmos-2 model, developed by Microsoft, is licensed under an [MIT license](https://github.com/microsoft/unilm/blob/master/LICENSE).
## 🏆 Contributing
We love your input! Please see the core Autodistill [contributing guide](https://github.com/autodistill/autodistill/blob/main/CONTRIBUTING.md) to get started. Thank you 🙏 to all our contributors!
Raw data
{
"_id": null,
"home_page": "https://github.com/autodistill/autodistill-kosmos-2",
"name": "autodistill-kosmos-2",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "",
"author": "Roboflow",
"author_email": "support@roboflow.com",
"download_url": "https://files.pythonhosted.org/packages/34/bb/4c354bb3faa80abac8d3b76fb4672a7f9678270c75ff72257dfbd9384bc5/autodistill-kosmos-2-0.1.1.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <p>\n <a align=\"center\" href=\"\" target=\"_blank\">\n <img\n width=\"850\"\n src=\"https://media.roboflow.com/open-source/autodistill/autodistill-banner.png\"\n >\n </a>\n </p>\n</div>\n\n# Autodistill Kosmos-2 Module\n\nThis repository contains the code supporting the Kosmos-2 base model for use with [Autodistill](https://github.com/autodistill/autodistill).\n\n[Kosmos-2](https://github.com/microsoft/unilm/tree/master/kosmos-2), developed by Microsoft, is a multimodal language model that you can use for zero-shot object detection. You can use Kosmos-2 with autodistill for object detection.\n\nRead the full [Autodistill documentation](https://autodistill.github.io/autodistill/).\n\nRead the [Kosmos-2 Autodistill documentation](https://autodistill.github.io/autodistill/base_models/kosmos_2/).\n\n## Installation\n\nTo use Kosmos-2 with autodistill, you need to install the following dependency:\n\n\n```bash\npip3 install autodistill-kosmos-2\n```\n\n## Quickstart\n\n```python\nfrom autodistill_kosmos_2 import Kosmos2\n\n# define an ontology to map class names to our Kosmos2 prompt\n# the ontology dictionary has the format {caption: class}\n# where caption is the prompt sent to the base model, and class is the label that will\n# be saved for that caption in the generated annotations\n# then, load the model\nbase_model = Kosmos2(\n ontology=CaptionOntology(\n {\n \"person\": \"person\",\n \"a forklift\": \"forklift\"\n }\n )\n)\n\npredictions = base_model.predict(\"./example.png\")\n\nbase_model.label(\"./context_images\", extension=\".jpeg\")\n```\n\n\n## License\n\nThis package is implemented using the [Transformers Kosmos-2 implementation](https://huggingface.co/microsoft/kosmos-2-patch14-224). The underlying Kosmos-2 model, developed by Microsoft, is licensed under an [MIT license](https://github.com/microsoft/unilm/blob/master/LICENSE).\n\n## \ud83c\udfc6 Contributing\n\nWe love your input! Please see the core Autodistill [contributing guide](https://github.com/autodistill/autodistill/blob/main/CONTRIBUTING.md) to get started. Thank you \ud83d\ude4f to all our contributors!\n",
"bugtrack_url": null,
"license": "",
"summary": "Kosmos-2 base model for use with Autodistill.",
"version": "0.1.1",
"project_urls": {
"Homepage": "https://github.com/autodistill/autodistill-kosmos-2"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "71ce5217936d6abd316676eaf4e5925cdca23af297640016e21812892d6f2c20",
"md5": "8e7eb1a4eca200e565f648264348227d",
"sha256": "67074b9dc1d405c10d3e28342bb7be7a3476a29014733e20b89238b6bc06a3a3"
},
"downloads": -1,
"filename": "autodistill_kosmos_2-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8e7eb1a4eca200e565f648264348227d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 4611,
"upload_time": "2024-01-30T21:18:29",
"upload_time_iso_8601": "2024-01-30T21:18:29.470925Z",
"url": "https://files.pythonhosted.org/packages/71/ce/5217936d6abd316676eaf4e5925cdca23af297640016e21812892d6f2c20/autodistill_kosmos_2-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "34bb4c354bb3faa80abac8d3b76fb4672a7f9678270c75ff72257dfbd9384bc5",
"md5": "f4419803939b5b3bcd28ab0af63494a4",
"sha256": "a86a0edfaf3ffd3f2569036f75c6b94bd7d42389bcf4cb44d6b65ad4d9cc65e9"
},
"downloads": -1,
"filename": "autodistill-kosmos-2-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "f4419803939b5b3bcd28ab0af63494a4",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 4328,
"upload_time": "2024-01-30T21:18:31",
"upload_time_iso_8601": "2024-01-30T21:18:31.723475Z",
"url": "https://files.pythonhosted.org/packages/34/bb/4c354bb3faa80abac8d3b76fb4672a7f9678270c75ff72257dfbd9384bc5/autodistill-kosmos-2-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-30 21:18:31",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "autodistill",
"github_project": "autodistill-kosmos-2",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "autodistill-kosmos-2"
}
JSON
