Florabelle — Flower Species Segmentation
This repository hosts the vision model that powers Florabelle, a flower vision + sales chatbot agent feeding a Spring AI tool-calling sales backend.
Built with Ultralytics YOLOv11. Full credit to Ultralytics for the open YOLO architecture and training tooling.
Model
- Architecture: YOLOv11-medium (instance segmentation)
- Task: Flower species instance segmentation, 126 classes
- Formats provided:
florabelle-seg.pt— Ultralytics checkpoint. Use for fine-tuning or retraining.florabelle-seg.onnx— ONNX export. Use for inference in any ONNX Runtime environment.
Training data
Trained on flowers_segmentation by flowersDetection, Roboflow Universe — 7,111 images across 126 flower species. Released under CC BY 4.0.
Usage
ONNX Runtime (inference only)
```python import onnxruntime as ort
session = ort.InferenceSession("florabelle-seg.onnx") outputs = session.run(None, {"images": input_tensor}) ```
Ultralytics (.pt — inference or further training)
```python from ultralytics import YOLO
model = YOLO("florabelle-seg.pt") results = model.predict("flower_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). Full credit to flowersDetection for the training dataset (CC BY 4.0).
- Downloads last month
- -
Model tree for beaunix/florabelle-vision
Base model
Ultralytics/YOLO11