Model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: agpl-3.0
|
| 3 |
+
library_name: ultralytics
|
| 4 |
+
pipeline_tag: image-segmentation
|
| 5 |
+
tags: [yolo, yolo26, onnx, instance-segmentation, coco]
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# yolo26n-seg (ONNX)
|
| 9 |
+
|
| 10 |
+
The official Ultralytics **YOLO26n-seg** COCO weights (`yolo26n-seg.pt`), exported unchanged to ONNX so they can run in the
|
| 11 |
+
browser with onnxruntime-web. Not fine-tuned.
|
| 12 |
+
|
| 13 |
+
| | |
|
| 14 |
+
|---|---|
|
| 15 |
+
| Input | `images` — float32 `[1, 3, 640, 640]`, RGB 0–1, letterboxed (pad 114) |
|
| 16 |
+
| Output 0 | `[1, 116, 8400]` = box `cx, cy, w, h` + 80 class scores + 32 mask coefficients. NMS is **not** included |
|
| 17 |
+
| Output 1 | `[1, 32, 160, 160]` mask prototypes — mask = sigmoid(coefficients · prototypes), cropped to the box |
|
| 18 |
+
| Size | ONNX 11.2 MB (opset 17, simplified) · source `.pt` 6.7 MB |
|
| 19 |
+
| Classes | COCO 80 |
|
| 20 |
+
|
| 21 |
+
Used by the model-card site [AI Models Organize](https://ai-models-organize.vercel.app/) (YOLO26n-seg card → «돌려보기»).
|
| 22 |
+
|
| 23 |
+
## License
|
| 24 |
+
|
| 25 |
+
AGPL-3.0, inherited from Ultralytics YOLO.
|