Object Detection
ultralytics
English
agriculture
weed-detection
yolo
yolov8
yolo26
precision-agriculture
research
Instructions to use Rmano-Rudeson/weedscan-kz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use Rmano-Rudeson/weedscan-kz 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("Rmano-Rudeson/weedscan-kz", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Download predict.py from Rmano-Rudeson/weedscan-kz: direct link, hf CLI and curl.
- Browser
- Download file 1.36 kB
-
https://huggingface.co/Rmano-Rudeson/weedscan-kz/resolve/main/predict.py
- Command line
-
hf download hf://Rmano-Rudeson/weedscan-kz/predict.py
-
curl -L -o predict.py https://huggingface.co/Rmano-Rudeson/weedscan-kz/resolve/main/predict.py
1.36 kB
| """Run an explicitly selected, trained WeedScan KZ checkpoint.""" | |
| import argparse | |
| import os | |
| from pathlib import Path | |
| REPO_ID = "Rmano-Rudeson/weedscan-kz" | |
| VARIANTS = ("yolov26n-10class", "yolov8n-15class", "yolov8n-5class") | |
| def load_model(variant="yolov26n-10class", model_path=None): | |
| from ultralytics import YOLO | |
| from huggingface_hub import hf_hub_download | |
| if variant not in VARIANTS: | |
| raise ValueError(f"Unknown variant: {variant}") | |
| path = model_path or os.environ.get("WEEDSCAN_MODEL_PATH") | |
| if path: | |
| if not Path(path).is_file(): | |
| raise FileNotFoundError(path) | |
| else: | |
| path = hf_hub_download(REPO_ID, f"models/{variant}/best.pt") | |
| return YOLO(str(path)) | |
| def main(): | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument("--image", required=True) | |
| parser.add_argument("--variant", choices=VARIANTS, default=VARIANTS[0]) | |
| parser.add_argument("--model-path") | |
| parser.add_argument("--device", default="cpu") | |
| args = parser.parse_args() | |
| if not Path(args.image).is_file(): | |
| parser.error("Image file does not exist") | |
| model = load_model(args.variant, args.model_path) | |
| results = model.predict(args.image, device=args.device, verbose=False) | |
| for result in results: | |
| print(result.to_json()) | |
| if __name__ == "__main__": | |
| main() | |