orosense_elev

LucasTakanori/orosense_elev

orosense_elev is a image-to-image model from LucasTakanori. Use it when you need one image transformed into another. The card lists the license as apache-2.0.

YOLO11n-pose model specialized for tongue elevation detection. Trained on frontal oral-motor recordings from a clinical tongue ROM dataset.

Downloads · 30 days

2% of all-time downloads

All-time downloads

Public

Repo size

5.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin5.7 MB · 97%

At a glance

Task: Image-to-Image
License: apache-2.0
Access: Public
Created: May 19, 2026
Updated: May 19, 2026
SHA: c5739ad5

Model card

From the Hugging Face model README

OroSense — Elevation Model (CoreML)

YOLO11n-pose model specialized for tongue elevation detection. Trained on frontal oral-motor recordings from a clinical tongue ROM dataset.

Model Details

Property	Value
Architecture	YOLO11n-pose
Input size	1280 × 1280
Keypoints	4
Format	CoreML (.mlpackage)
Training tasks	`elev`
Epochs	50
Augmentation	Heavy (rotation, scale, HSV, mosaic, mixup)

Keypoints

Index	Name	Description
0	left_commissure	Left corner of the mouth (MediaPipe LM 61)
1	right_commissure	Right corner of the mouth (MediaPipe LM 291)
2	tongue_tip	Annotated tongue tip position
3	upper_lip	Upper lip center / vermilion border (MediaPipe LM 0)

Usage (Swift / iOS)

import CoreML
import Vision

let model = try best(configuration: MLModelConfiguration())
let request = VNCoreMLRequest(model: try VNCoreMLModel(for: model.model))
// input: 1280×1280 RGB image

Training Metrics (best epoch)

Metric	Value
Box mAP50	0.991
Box mAP50-95	0.806
Pose mAP50	0.993
Pose mAP50-95	0.983

Part of OroSense

This model is one of three task-specialized models:

orosense_lat — lateralization
orosense_elev — elevation (this model)
orosense_side — side-view protrusion

Task: Image-to-Image
License: apache-2.0
Created: May 19, 2026
Updated: May 19, 2026