Downloads · 30 days
341
45% of all-time downloads
koppolusameer/yolo11n-basketball-court-keypoints
yolo11n-basketball-court-keypoints is a keypoint detection model from koppolusameer. Use it for the keypoint detection task on the model card, and read the license before you ship it in a product. It is set up for ultralytics. The card lists the license as agpl-3.0.
Fine-tuned yolo11n-pose.pt on koppolusameer/basketball-keypoint-detection-yolov8 (48-slot court skeleton) to detect court landmarks in broadcast frames.
Downloads · 30 days
341
45% of all-time downloads
All-time downloads
751
Public
Repo size
7.9 MB
Likes
0
Public
Click a slice to open those files.
.pt7.9 MB · 100%
From the Hugging Face model README
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.
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