Instructions to use ogaith/YOLOv8s-dog-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use ogaith/YOLOv8s-dog-detection with ultralytics:
from ultralytics import YOLOvv8 model = YOLOvv8.from_pretrained("ogaith/YOLOv8s-dog-detection") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| base_model: Ultralytics/YOLOv8 | |
| tags: | |
| - ultralytics | |
| - object-detection | |
| - yolo | |
| - yolov8 | |
| - dog | |
| pipeline_tag: object-detection | |
| library_name: ultralytics | |
| # 🐶 YOLOv8 Dog Detector | |
| This repository contains a finetuned **YOLOv8** model for **detecting dogs** in images. | |
| - **Model:** `best.pt` | |
| - **Dataset:** Google Open Images v7 (~4,000 dog instances) | |
| - **Task:** Object Detection (1 class: `dog`) | |
| --- | |
| ## 📦 Installation | |
| ```bash | |
| pip install ultralytics | |
| ``` | |
| ## 🚀 CLI Usage (recommended for quick testing) | |
| ```bash | |
| yolo detect predict \ | |
| model=best.pt \ | |
| source="assets/runs/detect/val/example1.jpg" \ | |
| imgsz=640 \ | |
| conf=0.25 \ | |
| save=True | |
| ``` | |
| Batch infer on folder | |
| ```bash | |
| yolo detect predict model=best.pt source="images_folder/" imgsz=640 conf=0.25 save=True | |
| ``` | |
| ## 🐍 Python Usage | |
| ```bash | |
| from ultralytics import YOLO | |
| # Load model | |
| model = YOLO("best.pt") | |
| # Run prediction | |
| results = model.predict( | |
| source="assets/runs/detect/val/example1.jpg", | |
| conf=0.25, | |
| imgsz=640 | |
| ) | |
| # Display or save result | |
| results[0].show() # display | |
| # results[0].save() # save to file | |
| ``` | |