Instructions to use camstack/camstack-trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use camstack/camstack-trainer with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("camstack/camstack-trainer", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
camstack-train 0.1.0: YOLOv9 root detector fine-tune (job.json in, result.json + bundle.tar out)
ebeed67 verified Download camstack_train/__init__.py from camstack/camstack-trainer: direct link, hf CLI and curl.
- Browser
- Download file 386 Bytes
-
https://huggingface.co/camstack/camstack-trainer/resolve/main/camstack_train/__init__.py
- Command line
-
hf download hf://camstack/camstack-trainer/camstack_train/__init__.py
-
curl -L -o __init__.py https://huggingface.co/camstack/camstack-trainer/resolve/main/camstack_train/__init__.py
386 Bytes
| """CamStack trainer: fine-tune a root detector on a hub's annotated export. | |
| The hub never imports this package. It talks to it through files only: | |
| ``job.json`` + ``dataset.tar`` in, ``bundle.tar`` + ``result.json`` out, and | |
| ``CAMSTACK_EVENT`` lines on stdout. Ultralytics (AGPL-3.0) is imported only by | |
| ``train_det`` and the export steps, inside this image. | |
| """ | |
| __version__ = "0.1.0" | |