Upload yolo26s fine-tuned model (.pt, .onnx, model card)

README.md

@@ -0,0 +1,49 @@
+# Model Card — American Black Bear (*Ursus americanus*)
+
+Single-class detection model for American Black Bear, fine-tuned from the Ultralytics
+YOLO26s backbone (pretrained on COCO).
+
+**Model file:** `yolo26s_finetuned_black_bear_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 | 157 |
+| val   | 19 |
+| test  | 21 |
+
+## Performance
+
+Evaluated on the held-out validation set (best checkpoint).
+
+| Metric | Value |
+|--------|------:|
+| mAP50 | 0.8077 |
+| mAP50-95 | 0.7152 |
+
+## Usage
+
+```python
+from ultralytics import YOLO
+model = YOLO("models/black_bear/yolo26s_finetuned_black_bear_by_J.Gong_uwyo_2026-05-28.pt")
+results = model.predict("image.jpg", conf=0.25)
+```

yolo26s_finetuned_black_bear_by_J.Gong_uwyo_2026-05-28.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ec9d202a53149100fd02bcdb43392458a73f95d7360cdb97f468cf864dc7d8
+size 38120075

yolo26s_finetuned_black_bear_by_J.Gong_uwyo_2026-05-28.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cf85746e53bc53e72defe92650ebcc3f56124071580d03d650c4292f51a76f
+size 20330821