Instructions to use gfermoto/birdlense-birds-eu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use gfermoto/birdlense-birds-eu with ultralytics:
# Couldn't find a valid YOLO version tag. # Replace XX with the correct version. from ultralytics import YOLOvXX model = YOLOvXX.from_pretrained("gfermoto/birdlense-birds-eu") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
metadata
license: cc-by-nc-4.0
datasets:
- gfermoto/birds-eu-merged
tags:
- image-classification
- birds
- europe
- birdlense
- yolo
- ultralytics
- scientific-name
pipeline_tag: image-classification
library_name: ultralytics
BirdLense Birds EU — YOLO11n-cls
Классификатор европейских птиц для BirdLense Hub. ~491 вид, формат Scientific (Common) — совместим с Frigate и BirdNET.
Модель
| Параметр | Значение |
|---|---|
| Архитектура | YOLO11n-cls (Ultralytics) |
| Классов | ~491 вид птиц |
| Размер | ~4.5 MB |
| Метрики (val) | top1 ~85.3%, top5 ~91.9% |
Датасет
Обучена на gfermoto/birds-eu-merged:
- birds-525 (Hugging Face)
- iNaturalist Europe (place_id=96372)
- ~17 800 train, ~4 600 val изображений
Использование
Ultralytics
from ultralytics import YOLO
model = YOLO("gfermoto/birdlense-birds-eu", task="classify")
results = model("bird.jpg")
Скачать в BirdLense
huggingface-cli download gfermoto/birdlense-birds-eu best.pt --local-dir app/processor/models/classification/weights
Лицензия
CC BY-NC 4.0. Датасет: gfermoto/birds-eu-merged.