AppleYieldCrop — Orchard Apple Counting Model
This repository hosts the vision model that powers AppleYieldCrop, an orchard app that counts apples for yield estimation.
Built with Ultralytics YOLOv8. Full credit to Ultralytics for the open YOLO architecture and training tooling.
Model
- Architecture: YOLOv8-medium (object detection)
- Task: Apple detection/counting
- Formats provided:
appleyieldcrop-det.pt— Ultralytics checkpoint. Use for fine-tuning or retraining.appleyieldcrop-det.onnx— ONNX export. Use for inference in any ONNX Runtime environment.
Training data
Extended dataset (~990 images), built on top of a ~640-image base dataset originally created by Arfiani Nur Sayidah on Roboflow Universe ("Apple Sorting" dataset lineage, CC BY 4.0), forked and expanded by beaunix with an additional ~300 self-annotated images (own bounding boxes) to improve orchard-scene generalization.
Usage
ONNX Runtime (inference only)
```python import onnxruntime as ort
session = ort.InferenceSession("appleyieldcrop-det.onnx") outputs = session.run(None, {"images": input_tensor}) ```
Ultralytics (.pt — inference or further training)
```python from ultralytics import YOLO
model = YOLO("appleyieldcrop-det.pt") results = model.predict("orchard_photo.jpg") ```
License
Released under AGPL-3.0, in line with the Ultralytics YOLO license this model was trained with (no Enterprise license was purchased). Training data credit: original base dataset by Arfiani Nur Sayidah (CC BY 4.0), extended by beaunix.
- Downloads last month
- -
Model tree for beaunix/apples-detection-model
Base model
Ultralytics/YOLOv8