https://github.com/autodistill/autodistill-vit
ViT module for use with autodistill.
https://github.com/autodistill/autodistill-vit
autodistill computer-vision vision-transformer vit
Last synced: 2 months ago
JSON representation
ViT module for use with autodistill.
- Host: GitHub
- URL: https://github.com/autodistill/autodistill-vit
- Owner: autodistill
- License: apache-2.0
- Created: 2023-06-08T06:45:31.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-06-30T08:37:38.000Z (almost 2 years ago)
- Last Synced: 2025-04-14T12:13:16.563Z (2 months ago)
- Topics: autodistill, computer-vision, vision-transformer, vit
- Language: Python
- Homepage: https://docs.autodistill.com
- Size: 11.7 KB
- Stars: 5
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Autodistill ViT Module
This repository contains the code supporting the ViT target model for use with [Autodistill](https://github.com/autodistill/autodistill).
[ViT](https://huggingface.co/google/vit-base-patch16-224-in21k) is a classification model pre-trained on ImageNet-21k, developed by Google. You can train ViT classification models using Autodistill.
Read the full [Autodistill documentation](https://autodistill.github.io/autodistill/).
Read the [ViT Autodistill documentation](https://autodistill.github.io/autodistill/target_models/vit/).
## Installation
To use the ViT target model, you will need to install the following dependency:
```bash
pip3 install autodistill-vit
```
## Quickstart
```python
from autodistill_vit import ViT
target_model = ViT()
# train a model from a classification folder structure
target_model.train("./context_images_labeled/", epochs=200)
# run inference on the new model
pred = target_model.predict("./context_images_labeled/train/images/dog-7.jpg", conf=0.01)
```
## License
The code in this repository is licensed under an [Apache 2.0 license](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!