Okra Seg Detector
Single-class okra instance-segmentation weights, fine-tuned for a humanoid robot (Unitree G1) okra-harvest perception pipeline. Two architectures trained under identical data/masks/hyperparameters for comparison:
Model source
- Kind
- Other
- File size
- 5.74–6.48 MB
- Version
- vOkra11n seg
- Updated
- Oct 4, 2026
- Source
- Hugging Face
Source description
Okra Segmentation Detector (YOLO11n-seg / YOLOv8n-seg)
Single-class okra instance-segmentation weights, fine-tuned for a humanoid robot (Unitree G1) okra-harvest perception pipeline. Two architectures trained under identical data/masks/hyperparameters for comparison:
| File | Base model | Params | Size |
|---|---|---|---|
okra11n-seg.pt | yolo11n-seg | ~2.9M | 5.7 MB |
okra8n-seg.pt | yolov8n-seg | ~3.4M | 6.5 MB |
Results (validation: 440 images, 1011 okra instances)
| Metric | okra11n-seg | okra8n-seg |
|---|---|---|
| Box mAP@50 | 0.906 | 0.901 |
| Box mAP@50-95 | 0.824 | 0.818 |
| Mask mAP@50 | 0.904 | 0.899 |
| Mask mAP@50-95 | 0.790 | 0.786 |
| Mask precision | 0.950 | 0.921 |
| Mask recall | 0.826 | 0.835 |
The two are essentially on par; yolo11n-seg is marginally ahead on mAP and precision and is smaller, while yolov8n-seg has slightly higher recall. Note: mask labels were SAM-generated (see below), so mask mAP measures agreement with the SAM teacher masks rather than against hand-drawn ground-truth contours.
How it was made
- Data: 2,923 okra images (112 real field photos + 2,811 Roboflow-augmented),
single class
okra. Annotations were bounding boxes; converted to polygon masks with SAM 2.1-large (ultralytics.data.converter.yolo_bbox2segment). - Split: 2,483 train / 440 val, grouped by source image (augmentation variants kept in the same split to avoid validation leakage), stratified real vs synthetic.
- Training: ultralytics 8.4.14,
100 epochs,
imgsz=640,batch=16, single A10G GPU,seed=0.
Usage
from ultralytics import YOLO
model = YOLO("okra11n-seg.pt") # or okra8n-seg.pt
results = model.predict("field.jpg", conf=0.30, retina_masks=True)
for r in results:
print(r.boxes.xyxy, r.boxes.conf) # okra boxes + confidence
print(r.masks.xy) # okra polygon masks
Recommended ultralytics version for inference: 8.4.14 (matches training).
Intended use & limitations
- Built for okra detection/segmentation in greenhouse/field harvest scenes, including green-on-green (okra against foliage). Detects okra pods; flowers are intentionally not flagged.
- Single class only (
okra). Not validated for ripeness grading. - Mask supervision is SAM-derived, not human-traced.
License
Derived from Ultralytics YOLO pretrained weights — AGPL-3.0.
Sources
1 source
Sources
1 sourceVerified Aug 9
Model artifacts
2 artifacts
Model artifacts
2 artifactsSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: agpl-3.0 tags: - ultralytics - yolo - yolo11 - yolov8 - object-detection - instance-segmentation - agriculture - okra library_name: ultralytics pipeline_tag: image-segmentation --- # Okra Segmentation Detector (YOLO11n-seg / YOLOv8n-seg) Single-class **okra** instance-segmentation weights, fine-tuned for a humanoid robot (Unitree G1) okra-harvest perception pipeline. Two architectures trained under identical data/masks/hyperparameters for comparison: | File | Base model | Params | Size | |---|---|---|---| | `okra11n-seg.pt` | `yolo11n-seg` | ~2.9M | 5.7 MB | | `okra8n-seg.pt` | `yolov8n-seg` | ~3.4M | 6.5 MB | ## Results (validation: 440 images, 1011 okra instances) | Metric | **okra11n-seg** | **okra8n-seg** | |---|---|---| | Box mAP@50 | **0.906** | 0.901 | | Box mAP@50-95 | **0.824** | 0.818 | | Mask mAP@50 | **0.904** | 0.899 | | Mask mAP@50-95 | **0.790** | 0.786 | | Mask precision | **0.950** | 0.921 | | Mask recall | 0.826 | **0.835** | The two are essentially on par; **yolo11n-seg is marginally ahead** on mAP and precision and is smaller, while yolov8n-seg has slightly higher recall. Note: mask labels were SAM-generated (see below), so mask mAP measures agreement with the SAM teacher masks rather than against hand-drawn ground-truth contours. ## How it was made - **Data:** 2,923 okra images (112 real field photos + 2,811 Roboflow-augmented), single class `okra`. Annotations were **bounding boxes**; converted to polygon masks with **SAM 2.1-large** (`ultralytics.data.converter.yolo_bbox2segment`). - **Split:** 2,483 train / 440 val, grouped by source image (augmentation variants kept in the same split to avoid validation leakage), stratified real vs synthetic. - **Training:** [ultralytics](https://github.com/ultralytics/ultralytics) **8.4.14**, 100 epochs, `imgsz=640`, `batch=16`, single A10G GPU, `seed=0`. ## Usage ```python from ultralytics import YOLO model = YOLO("okra11n-seg.pt") # or okra8n-seg.pt results = model.predict("field.jpg", conf=0.30, retina_masks=True) for r in results: print(r.boxes.xyxy, r.boxes.conf) # okra boxes + confidence print(r.masks.xy) # okra polygon masks ``` > Recommended ultralytics version for inference: **8.4.14** (matches training). ## Intended use & limitations - Built for okra detection/segmentation in greenhouse/field harvest scenes, including green-on-green (okra again...
Source context: 19 downloads · 0 likes · Pipeline image-segmentation · Library ultralytics · Repo Kota0612/okra-seg-detector
