| Name | autodistill-remote-clip JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | |
| Summary | Remote CLIP model for use with Autodistill |
| upload_time | 2023-12-05 09:20:30 |
| maintainer | |
| docs_url | None |
| author | Roboflow |
| requires_python | >=3.7 |
| license | |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<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 RemoteCLIP Module
This repository contains the code supporting the RemoteCLIP base model for use with [Autodistill](https://github.com/autodistill/autodistill).
[RemoteCLIP](https://github.com/ChenDelong1999/RemoteCLIP) is a vision-language CLIP model trained on remote sensing data. According to the RemoteCLIP README:
> RemoteCLIP outperforms previous SoTA by 9.14% mean recall on the RSICD dataset and by 8.92% on RSICD dataset. For zero-shot classification, our RemoteCLIP outperforms the CLIP baseline by up to 6.39% average accuracy on 12 downstream datasets.
Read the full [Autodistill documentation](https://autodistill.github.io/autodistill/).
Read the [RemoteCLIP Autodistill documentation](https://autodistill.github.io/autodistill/base_models/remoteclip/).
## Installation
To use RemoteCLIP with autodistill, you need to install the following dependency:
```bash
pip3 install autodistill-remote-clip
```
## Quickstart
```python
from autodistill_remote_clip import RemoteCLIP
from autodistill.detection import CaptionOntology
# define an ontology to map class names to our RemoteCLIP 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 = RemoteCLIP(
ontology=CaptionOntology(
{
"airport runway": "runway",
"countryside": "countryside",
}
)
)
predictions = base_model.predict("runway.jpg")
print(predictions)
```
## License
This Autodistill module is licensed under an MIT license. At the time of publishing this project, the RemoteCLIP model and weights had no attached license. Refer to the [RemoteCLIP repository](https://github.com/ChenDelong1999/RemoteCLIP) for the most up-to-date licensing information regarding the model.
## 🏆 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": "",
"name": "autodistill-remote-clip",
"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/80/86/890fbd474c320657936d9d05783fefff653fa54b490f2e546dab23788359/autodistill-remote-clip-0.1.2.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 RemoteCLIP Module\n\nThis repository contains the code supporting the RemoteCLIP base model for use with [Autodistill](https://github.com/autodistill/autodistill).\n\n[RemoteCLIP](https://github.com/ChenDelong1999/RemoteCLIP) is a vision-language CLIP model trained on remote sensing data. According to the RemoteCLIP README:\n\n> RemoteCLIP outperforms previous SoTA by 9.14% mean recall on the RSICD dataset and by 8.92% on RSICD dataset. For zero-shot classification, our RemoteCLIP outperforms the CLIP baseline by up to 6.39% average accuracy on 12 downstream datasets.\n\nRead the full [Autodistill documentation](https://autodistill.github.io/autodistill/).\n\nRead the [RemoteCLIP Autodistill documentation](https://autodistill.github.io/autodistill/base_models/remoteclip/).\n\n## Installation\n\nTo use RemoteCLIP with autodistill, you need to install the following dependency:\n\n```bash\npip3 install autodistill-remote-clip\n```\n\n## Quickstart\n\n```python\nfrom autodistill_remote_clip import RemoteCLIP\nfrom autodistill.detection import CaptionOntology\n\n# define an ontology to map class names to our RemoteCLIP 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 = RemoteCLIP(\n ontology=CaptionOntology(\n {\n \"airport runway\": \"runway\",\n \"countryside\": \"countryside\",\n }\n )\n)\n\npredictions = base_model.predict(\"runway.jpg\")\n\nprint(predictions)\n```\n\n## License\n\nThis Autodistill module is licensed under an MIT license. At the time of publishing this project, the RemoteCLIP model and weights had no attached license. Refer to the [RemoteCLIP repository](https://github.com/ChenDelong1999/RemoteCLIP) for the most up-to-date licensing information regarding the model.\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": "Remote CLIP model for use with Autodistill",
"version": "0.1.2",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4ae1f74804c290e02e6bab4ad2a12e8ce084d1614a09baabc467284b2c25dbf4",
"md5": "35ecf7f1c2eb68321bd5c3305d3d5880",
"sha256": "d23fddb063a513df0261bb039c60508f3441748b35ebf74e5434efa758adb840"
},
"downloads": -1,
"filename": "autodistill_remote_clip-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "35ecf7f1c2eb68321bd5c3305d3d5880",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 4585,
"upload_time": "2023-12-05T09:20:28",
"upload_time_iso_8601": "2023-12-05T09:20:28.329751Z",
"url": "https://files.pythonhosted.org/packages/4a/e1/f74804c290e02e6bab4ad2a12e8ce084d1614a09baabc467284b2c25dbf4/autodistill_remote_clip-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8086890fbd474c320657936d9d05783fefff653fa54b490f2e546dab23788359",
"md5": "14669b6260ade1fe0845da9d2275f04d",
"sha256": "6912eeaedf1dc7a36558894c2fff68fcd84c98198933abc13695830386d8ec15"
},
"downloads": -1,
"filename": "autodistill-remote-clip-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "14669b6260ade1fe0845da9d2275f04d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 4231,
"upload_time": "2023-12-05T09:20:30",
"upload_time_iso_8601": "2023-12-05T09:20:30.078310Z",
"url": "https://files.pythonhosted.org/packages/80/86/890fbd474c320657936d9d05783fefff653fa54b490f2e546dab23788359/autodistill-remote-clip-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-05 09:20:30",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "autodistill-remote-clip"
}
