Car Parts Segmentation M

--- base_model: - Ultralytics/YOLO26 datasets: - mitbersh/car-parts-segmentation-yolo pipeline_tag: image-segmentation --- # AutoInspect - Car Parts Segmentation (YOLO26) Модель для сегментации деталей автомобиля на изображении. Адаптирована под авто с повреждениями. Часть проекта [**AutoInspect**](https://github.com/DedovInside/AutoInspect/tree/ml/ml). ## Task Сегментация деталей автомобиля. ## Overview Модель построена на **YOLO26-m**. Основные параметры: - **Input image size:** `896` - **Number of classes:** `33` - **Side-aware classes:** да, модель различает `left_*` и `right_*` детали Модель обучалась в [Kaggle-ноутбуке](https://www.kaggle.com/code/brshtskmit/train-car-parts-segmentation-yolov26-m). ## Quick Start ### Installation ```bash pip install -U ultralytics huggingface_hub ``` ### Python Inference ```python from huggingface_hub import hf_hub_download from ultralytics import YOLO repo_id = "mitbersh/car-parts-segmentation" weights_path = hf_hub_download( repo_id=repo_id, filename="parts_segmentation.pt" ) model = YOLO(weights_path) results = model.predict( source="path/to/car_image.jpg", imgsz=896, conf=0.25, iou=0.7, save=True ) print(results) ``` ### Alternative: CLI Inference ```bash yolo segment predict \ model=parts_segmentation.pt \ source=path/to/car_image.jpg \ imgsz=896 \ conf=0.25 \ iou=0.7 \ save=True ```

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Repo mitbersh/car-parts-segmentation-m