Instructions to use Anderodri/celebrity_detection_yolov8n with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use Anderodri/celebrity_detection_yolov8n with ultralytics:
from ultralytics import YOLOvv8 model = YOLOvv8.from_pretrained("Anderodri/celebrity_detection_yolov8n") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
tags:
- yolov8
- object-detection
- computer-vision
- custom-dataset
- huggingface
- ultralytics
license: apache-2.0
datasets:
- custom
model-index:
- name: Celebrity Detection YOLOv8n
results:
- task:
type: object-detection
dataset:
name: Custom Dataset (Friends)
type: image
metrics:
- type: mAP
value: 0.98
- type: mAP50-95
value: 0.91
- type: precision
value: 0.96
- type: recall
value: 0.98
Celebrity Detection YOLOv8n
📄 Celebrity Detection YOLOv8n (English)
⬇ Scroll down for Español
This repository contains a YOLOv8n model trained to detect the main characters from the TV show Friends in images and videos. The model was trained on a custom dataset labeled using Amazon Rekognition.
📌 Model Details
- Model: YOLOv8n (pretrained on COCO, fine-tuned on Friends dataset)
- Classes:
- Matt LeBlanc (Joey)
- David Schwimmer (Ross)
- Matthew Perry (Chandler)
- Courteney Cox (Monica)
- Jennifer Aniston (Rachel)
- Dataset: Custom dataset generated from YouTube shorts of Friends episodes
- Training Images: ~13,000 (80% training, 20% validation)
- Hardware Used: Trained on GPU
- Frameworks & Libraries:
ultralytics
🏆 Model Performance
| Metric | Value |
|---|---|
| mAP@50 | 0.98 |
| mAP@50-95 | 0.91 |
| Precision | 0.96 |
| Recall | 0.98 |
Performance Curves:
📸 Example Detections
Incorrect/misclassified example (blonde woman mistaken for Jennifer Aniston):

📄 Modelo de Detección de Celebridades YOLOv8n (Español)
⬆ Scroll up for English
Este repositorio contiene un modelo YOLOv8n entrenado para detectar a los personajes principales de la serie Friends en imágenes y videos. El modelo fue entrenado en un conjunto de datos personalizado etiquetado con Amazon Rekognition.
🏆 Rendimiento del Modelo
| Métrica | Valor |
|---|---|
| mAP@50 | 0.98 |
| mAP@50-95 | 0.91 |
| Precisión | 0.96 |
| Recall | 0.98 |
Curvas de Rendimiento:
📸 Ejemplos de Detección
Imágenes detectadas correctamente:

Ejemplo de detección errónea (mujer rubia identificada incorrectamente como Jennifer Aniston):

¡Déjanos saber tus comentarios o mejoras! 🚀



