ModelPrésentéExterne

Yolo11n Basketball Court Keypoints

Fine-tuned yolo11n-pose.pt on koppolusameer/basketball-keypoint-detection-yolov8 (48-slot court skeleton) to detect court landmarks in broadcast frames.

Sourcehuggingface.co/koppolusameer/yolo11n-basketball-court-keypoints/tree/6cb899251439982067a81baa225b33f45f335981

TypeOtherVersionRevision 6cb8992BClasse

Source du modèle

Type: Other
Taille du fichier: 7,57 MB
Version: vRevision 6cb8992
Mis à jour: 10 oct. 2026
Téléchargements: 126
Source: Hugging Face

Description de la source

YOLO11n basketball court keypoint detector

Fine-tuned yolo11n-pose.pt on koppolusameer/basketball-keypoint-detection-yolov8 (48-slot court skeleton) to detect court landmarks in broadcast frames.

Outputs keypoints in PIXEL coordinates. Converting to court coordinates (homography) is a separate downstream step requiring an index->court-location map.

Load & run

from ultralytics import YOLO
from huggingface_hub import hf_hub_download
weights = hf_hub_download("koppolusameer/yolo11n-basketball-court-keypoints", "best.pt")
model = YOLO(weights)
r = model("frame.jpg")[0]
kxy   = r.keypoints.xy[0].cpu().numpy()    # (48,2) pixel coords
kconf = r.keypoints.conf[0].cpu().numpy()  # (48,) confidence

Sources

1 source

Hugging FacePrincipalVersion 6cb899251439982067a81baa225b33f45f335981

huggingface.co/koppolusameer/yolo11n-basketball-court-keypoints/tree/6cb899251439982067a81baa225b33f45f335981

Vérifié 10 oct.

Artefacts du modèle

1 artefact

best.pt

pt · 7,57 MB · SHA-256 68e5faf5fb53…0064 · Hugging Face

Download file

Extraits de sources

3 extraits

Readme1 aoûthuggingface.co/koppolusameer/yolo11n-basketball-court-keypoints

--- license: agpl-3.0 tags: [ultralytics, yolo11, pose, keypoint-detection, basketball, court-registration] library_name: ultralytics --- # YOLO11n basketball court keypoint detector Fine-tuned `yolo11n-pose.pt` on `koppolusameer/basketball-keypoint-detection-yolov8` (48-slot court skeleton) to detect court landmarks in broadcast frames. Outputs keypoints in PIXEL coordinates. Converting to court coordinates (homography) is a separate downstream step requiring an index->court-location map. ## Load & run ```python from ultralytics import YOLO from huggingface_hub import hf_hub_download weights = hf_hub_download("koppolusameer/yolo11n-basketball-court-keypoints", "best.pt") model = YOLO(weights) r = model("frame.jpg")[0] kxy = r.keypoints.xy[0].cpu().numpy() # (48,2) pixel coords kconf = r.keypoints.conf[0].cpu().numpy() # (48,) confidence ```

Note10 oct.huggingface.co/koppolusameer/yolo11n-basketball-court-keypoints

Source context: 126 downloads · 0 likes · Pipeline keypoint-detection · Library ultralytics · Repo koppolusameer/yolo11n-basketball-court-keypoints

Note1 aoûthuggingface.co/koppolusameer/yolo11n-basketball-court-keypoints

Source context: 70 downloads · 0 likes · Pipeline keypoint-detection · Library ultralytics · Repo koppolusameer/yolo11n-basketball-court-keypoints