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
File size: 386 Bytes
ebeed67 | 1 2 3 4 5 6 7 8 9 10 | """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"
|