https://github.com/autodistill/autodistill-detr
DETR (resnet-50) module for use with Autodistill.
https://github.com/autodistill/autodistill-detr
autodistill computer-vision detr
Last synced: 2 months ago
JSON representation
DETR (resnet-50) module for use with Autodistill.
- Host: GitHub
- URL: https://github.com/autodistill/autodistill-detr
- Owner: autodistill
- License: apache-2.0
- Created: 2023-06-06T14:13:21.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-10-16T10:31:12.000Z (over 1 year ago)
- Last Synced: 2025-04-14T12:13:20.859Z (2 months ago)
- Topics: autodistill, computer-vision, detr
- Language: Python
- Homepage: https://docs.autodistill.com
- Size: 17.6 KB
- Stars: 3
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Autodistill DETR Module
This repository contains the code supporting the DETR base model for use with [Autodistill](https://github.com/autodistill/autodistill).
[DETR](https://huggingface.co/docs/transformers/model_doc/detr) is a transformer-based computer vision model you can use for object detection. Autodistill supports training a model using the Meta Research Resnet 50 checkpoint.
Read the full [Autodistill documentation](https://autodistill.github.io/autodistill/).
Read the [DETR Autodistill documentation](https://autodistill.github.io/autodistill/target_models/detr/).
## Installation
To use DETR with autodistill, you need to install the following dependency:
```bash
pip3 install autodistill-detr
```
## Quickstart
```python
from autodistill_detr import DETR
# load the model
target_model = DETR()
# train for 10 epochs
target_model.train("./roads", epochs=10)
# run inference on an image
target_model.predict("./roads/valid/-3-_jpg.rf.bee113a09b22282980c289842aedfc4a.jpg")
```
## License
This project is licensed under an [Apache 2.0 license](LICENSE). See the [Hugging Face model card for the DETR Resnet 50](https://huggingface.co/facebook/detr-resnet-50) model for more information on the model 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!