<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 MetaCLIP Module
This repository contains the code supporting the MetaCLIP base model for use with [Autodistill](https://github.com/autodistill/autodistill).
[MetaCLIP](https://github.com/facebookresearch/MetaCLIP), developed by Meta AI Research, is a computer vision model trained using pairs of images and text. The model was described in the [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) paper. You can use MetaCLIP with autodistill for image classification.
Read the full [Autodistill documentation](https://autodistill.github.io/autodistill/).
Read the [MetaCLIP Autodistill documentation](https://autodistill.github.io/autodistill/base_models/metaclip/).
## Installation
To use MetaCLIP with autodistill, you need to install the following dependency:
```bash
pip3 install autodistill-metaclip
```
## Quickstart
### get predictions
```python
from autodistill_metaclip import MetaCLIP
# define an ontology to map class names to our MetaCLIP 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 = MetaCLIP(
ontology=CaptionOntology(
{
"person": "person",
"a forklift": "forklift"
}
)
)
results = base_model.predict("./image.png")
print(results)
```
### calculate and compare embeddings
```python
from autodistill_metaclip import MetaCLIP
base_model = MetaCLIP(None)
text = base_model.embed_text("coffee")
image = base_model.embed_image("coffeeshop.jpg")
print(base_model.compare(text, image))
```
## License
This project was licensed under a Creative Commons [Attribution-NonCommercial 4.0 International](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-metaclip",
"name": "autodistill-metaclip",
"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/56/12/c9c4f7323713c101b028a411af5c300ef0912840acfe33af9529cf82867e/autodistill-metaclip-0.1.3.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 MetaCLIP Module\n\nThis repository contains the code supporting the MetaCLIP base model for use with [Autodistill](https://github.com/autodistill/autodistill).\n\n[MetaCLIP](https://github.com/facebookresearch/MetaCLIP), developed by Meta AI Research, is a computer vision model trained using pairs of images and text. The model was described in the [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) paper. You can use MetaCLIP with autodistill for image classification.\n\nRead the full [Autodistill documentation](https://autodistill.github.io/autodistill/).\n\nRead the [MetaCLIP Autodistill documentation](https://autodistill.github.io/autodistill/base_models/metaclip/).\n\n## Installation\n\nTo use MetaCLIP with autodistill, you need to install the following dependency:\n\n```bash\npip3 install autodistill-metaclip\n```\n\n## Quickstart\n\n### get predictions\n\n```python\nfrom autodistill_metaclip import MetaCLIP\n\n# define an ontology to map class names to our MetaCLIP 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 = MetaCLIP(\n ontology=CaptionOntology(\n {\n \"person\": \"person\",\n \"a forklift\": \"forklift\"\n }\n )\n)\n\nresults = base_model.predict(\"./image.png\")\nprint(results)\n```\n\n### calculate and compare embeddings\n\n```python\nfrom autodistill_metaclip import MetaCLIP\n\nbase_model = MetaCLIP(None)\n\ntext = base_model.embed_text(\"coffee\")\nimage = base_model.embed_image(\"coffeeshop.jpg\")\n\nprint(base_model.compare(text, image))\n```\n\n## License\n\nThis project was licensed under a Creative Commons [Attribution-NonCommercial 4.0 International](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": "MetaCLIP base model for use with Autodistill.",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/autodistill/autodistill-metaclip"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1a826547a18c55e628e85b83c219230cede1b6a1150c22f529acf9042d4e4948",
"md5": "954c00365b0d201df4953980d944848e",
"sha256": "7ce6fa139e3a8a236b59a1dfd6713faf4584c9dfd334c8544fbf6cf59f5ca2e7"
},
"downloads": -1,
"filename": "autodistill_metaclip-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "954c00365b0d201df4953980d944848e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 10149,
"upload_time": "2023-12-05T09:10:43",
"upload_time_iso_8601": "2023-12-05T09:10:43.043151Z",
"url": "https://files.pythonhosted.org/packages/1a/82/6547a18c55e628e85b83c219230cede1b6a1150c22f529acf9042d4e4948/autodistill_metaclip-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5612c9c4f7323713c101b028a411af5c300ef0912840acfe33af9529cf82867e",
"md5": "7f41b37853e18d6c29ece27dcdbcd26b",
"sha256": "3826aa55404601047a5dda0f51aac787e4e77b9d2aff4156a237ced65b100d38"
},
"downloads": -1,
"filename": "autodistill-metaclip-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "7f41b37853e18d6c29ece27dcdbcd26b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 9727,
"upload_time": "2023-12-05T09:10:45",
"upload_time_iso_8601": "2023-12-05T09:10:45.718760Z",
"url": "https://files.pythonhosted.org/packages/56/12/c9c4f7323713c101b028a411af5c300ef0912840acfe33af9529cf82867e/autodistill-metaclip-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-05 09:10:45",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "autodistill",
"github_project": "autodistill-metaclip",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "autodistill-metaclip"
}
JSON
