add ball11n.pt ball detector and model card
Browse files- README.md +36 -0
- ball11n.pt +3 -0
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: agpl-3.0
|
| 3 |
+
tags:
|
| 4 |
+
- object-detection
|
| 5 |
+
- yolo
|
| 6 |
+
- ultralytics
|
| 7 |
+
- football
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# gst-python-ml football models
|
| 11 |
+
|
| 12 |
+
Weights for the football broadcast demo in [gst-python-ml](https://github.com/collabora/gst-python-ml). `demo/football/fetch_models.py` downloads them into `models/football/`.
|
| 13 |
+
|
| 14 |
+
| file | classes | input | role |
|
| 15 |
+
|---|---|---|---|
|
| 16 |
+
| `football.pt`, `football.onnx`, `football_fp16.onnx`, `football_int8.onnx` | ball, goalkeeper, player, referee | 640 | player detector |
|
| 17 |
+
| `ball11n.pt` | ball | 1280 | ball detector, run after the player detector |
|
| 18 |
+
|
| 19 |
+
## ball11n.pt
|
| 20 |
+
|
| 21 |
+
yolo11n fine-tuned from the ultralytics COCO weights for 40 epochs at imgsz 1280 on a one-class ball dataset of 15,357 training images. The player detector's own ball class is dropped in the demo in favour of this model.
|
| 22 |
+
|
| 23 |
+
| set | imgsz | P | R | mAP50 | mAP50-95 |
|
| 24 |
+
|---|---|---|---|---|---|
|
| 25 |
+
| SoccerNet v3 H250 test | 1280 | 0.774 | 0.708 | 0.701 | 0.327 |
|
| 26 |
+
| football-player-detection valid+test, ball only | 1280 | 0.921 | 0.850 | 0.888 | 0.407 |
|
| 27 |
+
|
| 28 |
+
Training data, all CC BY 4.0:
|
| 29 |
+
|
| 30 |
+
- SoccerNet v3 H250, Zenodo record [7808511](https://zenodo.org/records/7808511), ball labels only
|
| 31 |
+
- [martinjolif/football-ball-detection](https://huggingface.co/datasets/martinjolif/football-ball-detection)
|
| 32 |
+
- [martinjolif/football-player-detection](https://huggingface.co/datasets/martinjolif/football-player-detection), held out as the second evaluation set
|
| 33 |
+
|
| 34 |
+
## Licence
|
| 35 |
+
|
| 36 |
+
The weights derive from ultralytics YOLO and are released under AGPL-3.0 like the ultralytics package.
|
ball11n.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c1041f43806454083ad851fe2fbb3db48bc3d51a42430be219a22bedbb1714
|
| 3 |
+
size 5567578
|