Instructions to use datasidahmed/YOLOV8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use datasidahmed/YOLOV8 with ultralytics:
from ultralytics import YOLOvv8 model = YOLOvv8.from_pretrained("datasidahmed/YOLOV8") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "model": { | |
| "architecture": "YOLOv8n", | |
| "parameters": 3013188, | |
| "gflops": 8.2, | |
| "file_size_mb": 24.5, | |
| "task": "object-detection", | |
| "input_size": [640, 640], | |
| "framework": "Ultralytics 8.x", | |
| "num_classes": 12 | |
| }, | |
| "classes": { | |
| "0": "camouflage_soldier", | |
| "1": "weapon", | |
| "2": "military_tank", | |
| "3": "military_truck", | |
| "4": "military_vehicle", | |
| "5": "civilian", | |
| "6": "soldier", | |
| "7": "civilian_vehicle", | |
| "8": "military_artillery", | |
| "9": "trench", | |
| "10": "military_aircraft", | |
| "11": "military_warship" | |
| }, | |
| "training": { | |
| "base_model": "yolov8n.pt", | |
| "epochs": 100, | |
| "image_size": 640, | |
| "batch_size": 16, | |
| "optimizer": "AdamW", | |
| "conf_threshold": 0.40, | |
| "iou_threshold": 0.50 | |
| }, | |
| "validation_metrics": { | |
| "mAP50": 0.72, | |
| "mAP50_95": 0.48, | |
| "precision": 0.74, | |
| "recall": 0.68, | |
| "inference_speed_cpu_ms": 120 | |
| }, | |
| "repository": "https://huggingface.co/datasidahmed/YOLOV8", | |
| "author": "Sidahmed Melainin" | |
| } | |