Modelpublic

SuperSura/hand-gesture-yolo26n

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes176downloads

Model Card

Hand Gesture Recognition — YOLO26n

Fine-tuned YOLO26n for 12-class hand gesture recognition, trained on the HaGRID dataset.

Model Details

Attribute	Value
Architecture	YOLO26n (Ultralytics)
Classes	12
Input Size	800×800
Batch	48
Epochs	100
mAP50	0.994
mAP50-95	0.862
Weight Size	5.1 MB (FP32)

Classes

0: like      1: palm      2: fist       3: peace
4: ok        5: one       6: three      7: four
8: call      9: point    10: grip      11: middle_finger

Usage

python

from ultralytics import YOLO

model = YOLO("yolo26n_hand-gesture_12c_v1.pt")
results = model("hand.jpg")
results[0].show()

Training Parameters

—imgsz: 800
—batch: 48
—optimizer: auto (AdamW)
—device: CUDA (NVIDIA RTX 5070 Ti, 16 GB)
—cache: disk
—workers: 12
—patience: 0

Dataset

Trained on a subset of HaGRID (Hand Gesture Recognition Image Dataset), containing ~36,000 images across 12 gesture classes.

Performance Notes

The model converged around epoch 84 (mAP50-95=0.862) and remained stable through epoch 100. Suitable for real-time inference on consumer GPUs.