Instructions to use twincar-group2/twincar-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use twincar-group2/twincar-classifier with timm:
import timm model = timm.create_model("hf_hub:twincar-group2/twincar-classifier", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| library_name: pytorch | |
| tags: | |
| - image-classification | |
| - computer-vision | |
| - vehicle-classification | |
| - pytorch | |
| - timm | |
| license: mit | |
| # TwinCar Classifier | |
| TwinCar is a vehicle make and model recognition project developed for the Brainster Data Science Academy Machine Learning Final Project. | |
| ## Task | |
| The model predicts: | |
| - vehicle make | |
| - vehicle model | |
| - optionally production year | |
| ## Current status | |
| This repository is a placeholder for the final trained model and model card. | |
| Final contents will include: | |
| - model architecture | |
| - training dataset summary | |
| - validation metrics | |
| - robustness evaluation notes | |
| - usage instructions | |
| - limitations | |
| - links to GitHub, W&B, and demo Space | |
| ## Links | |
| - GitHub repo: https://github.com/Hristijan-kiko/twincar | |
| - W&B project: https://wandb.ai/hzlatevskii-brainster-data-science-academy/twincar | |
| - Demo Space: https://huggingface.co/spaces/twincar-group2/twincar-demo |