Downloads · 30 days
0
face_detection_yunet_2023mar
pollen-robotics/face_detection_yunet_2023mar
face_detection_yunet_2023mar is a object detection model from pollen-robotics. Use it when you need objects located in an image. The card lists the license as mit.
Unmodified redistribution of facedetectionyunet2023mar.onnx from the OpenCV Zoo.
Access
Public
Updated Jul 7, 2026
Repo size
233 KB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx233 KB · 99%
At a glance
- Task
- Object Detection
- License
- mit
- Access
- Public
- Created
- Jul 6, 2026
- Updated
- Jul 7, 2026
- SHA
- cae51054
Model card
From the Hugging Face model README
YuNet Face Detection — 2023mar
Unmodified redistribution of face_detection_yunet_2023mar.onnx from the
OpenCV Zoo.
YuNet is a light-weight, fast and accurate face detection model (WIDER Face: 0.834 AP_easy / 0.824 AP_medium / 0.708 AP_hard) that detects faces of roughly 10×10 to 300×300 px. This is the fixed-input-shape variant: OpenCV 4.x's DNN reshapes it to the input frame, while OpenCV 5.x's ONNX Runtime engine needs the dynamic 2026may variant.
Input
input — float32 tensor [1, 3, 640, 640] (fixed): a BGR image, NCHW layout, no normalization.
Output
12 per-stride detection heads for strides s ∈ {8, 16, 32}, each shaped [1, A, C]
with A = (640/s)² = 6400 / 1600 / 400 anchors:
| tensor | shape | meaning |
|---|---|---|
cls_{s} | [1, A, 1] | classification score |
obj_{s} | [1, A, 1] | objectness score |
bbox_{s} | [1, A, 4] | bounding-box regression |
kps_{s} | [1, A, 10] | 5 landmarks — right eye, left eye, nose, right/left mouth corner — as (x, y) |
cv2.FaceDetectorYN decodes these heads into an N × 15 array per face:
[x, y, w, h, 5 × (x, y), score].
License
MIT, following the upstream OpenCV Zoo.
@article{wu2023yunet,
title={YuNet: A Tiny Millisecond-level Face Detector},
author={Wu, Wei and Peng, Hanyang and Yu, Shiqi},
journal={Machine Intelligence Research},
volume={20}, number={5}, pages={656--665}, year={2023}, publisher={Springer}
}
- Task
- Object Detection
- License
- mit
- Created
- Jul 6, 2026
- Updated
- Jul 7, 2026