Downloads · 30 days
2
4% of all-time downloads
wildlife-moose
UWyo/wildlife-moose
wildlife-moose is a object detection model from UWyo. Use it when you need objects located in an image. It is set up for ultralytics. The card lists the license as cc-by-4.0.
Single-class detection model for Moose, fine-tuned from the Ultralytics YOLO26s backbone (pretrained on COCO).
All-time downloads
49
Public
Repo size
58.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx38.1 MB · 65%
At a glance
- Task
- Object Detection
- Library
- ultralytics
- License
- cc-by-4.0
- Access
- Public
- Created
- Jun 17, 2026
- Updated
- Jun 17, 2026
- SHA
- b522e607
Model card
From the Hugging Face model README
Model Card — Moose (Alces alces)
Single-class detection model for Moose, fine-tuned from the Ultralytics YOLO26s backbone (pretrained on COCO).
Model file: yolo26s_finetuned_moose_by_J.Gong_uwyo_2026-05-28.pt
Training Details
| Property | Value |
|---|---|
| Base model | yolo26s.pt (COCO pretrained, Ultralytics) |
| Architecture | YOLO26s |
| Input size | 640 × 640 |
| Epochs | 150 |
| Optimizer | MuSGD, lr=0.002, momentum=0.9 |
| Augmentation | mosaic=1.0, degrees=10°, scale=0.5, fliplr=0.5, hsv_h/s/v |
| Device | NVIDIA RTX 5000 Ada Generation (32 GB, CUDA 12.8) |
| Training date | 2026-05-28 |
| Author | Jian Gong, University of Wyoming |
Dataset
Images sourced from iNaturalist (research-grade observations). Bounding boxes generated by MegaDetector v5a (confidence ≥ 0.15). Split 80 / 10 / 10 train / val / test.
| Split | Images |
|---|---|
| train | 171 |
| val | 21 |
| test | 22 |
Performance
Evaluated on the held-out validation set (best checkpoint).
| Metric | Value |
|---|---|
| mAP50 | 0.8641 |
| mAP50-95 | 0.7408 |
Usage
from ultralytics import YOLO
model = YOLO("models/moose/yolo26s_finetuned_moose_by_J.Gong_uwyo_2026-05-28.pt")
results = model.predict("image.jpg", conf=0.25)
- Task
- Object Detection
- Library
- ultralytics
- License
- cc-by-4.0
- Created
- Jun 17, 2026
- Updated
- Jun 17, 2026