---
license: other
license_name: mixed-permissive
license_link: LICENSE.md
pipeline_tag: image-feature-extraction
tags:
  - face-detection
  - face-recognition
  - face-landmarks
  - ncnn
  - lightcella
---

# Lightcella Face Models (ncnn)

[ncnn](https://github.com/Tencent/ncnn)-format conversions of three permissively-licensed face
models, for on-device use on low-power hardware (Raspberry Pi 4 / NAS). Format conversion only — no
retraining. The detector and refiner were validated against their ONNX reference in onnxruntime.

| model | files | size | role | upstream | license |
|---|---|---|---|---|---|
| **YuNet** | `detector/yunet_2023mar.ncnn.{param,bin}` | 0.22 MB | face detection | [OpenCV Zoo `face_detection_yunet_2023mar`](https://github.com/opencv/opencv_zoo/tree/main/models/face_detection_yunet) | MIT (© 2020 Shiqi Yu) |
| **Face Mesh** | `refiner/mediapipe_facemesh_478.ncnn.{param,bin}` | 4.8 MB | 478 face landmarks | MediaPipe `face_landmarks_detector` (`face_landmarker.task`, 2023-05-03) | Apache-2.0 |
| **GhostFaceNet** | `embedder/ghostfacenet_w1.3_s2.ncnn.{param,bin}` | 8.1 MB | face embedding (512-d) | [HamadYA/GhostFaceNets](https://github.com/HamadYA/GhostFaceNets) W1.3 S2 ArcFace | MIT (© 2022 HamadYA) |

Each subdirectory carries its model **and its own `LICENSE`**. Repo license is `other` because the
files carry two MIT + one Apache-2.0 (map in [`LICENSE.md`](LICENSE.md)).

## I/O

| model | input | output |
|---|---|---|
| YuNet | RGB image, 640×640 | detection heads (cls/obj/bbox/kps) at strides 8/16/32 |
| Face Mesh | RGB face crop, 256×256 | 478 3D landmarks + presence score |
| GhostFaceNet | aligned RGB face, 112×112 | 512-d embedding |

Blob names follow the `pnnx` conversion (`in0` / `out0…`). ncnn param/bin format.

## Provenance

Converted with `tf2onnx` / `onnxsim` / `pnnx` and checked against onnxruntime. The exact upstream
source artifacts, SHA-256-pinned, are archived at
[`lightcella/face-pipeline-sources`](https://huggingface.co/lightcella/face-pipeline-sources).

## Attribution

Credit to the upstream authors — **YuNet** (Shiqi Yu, OpenCV Zoo), **MediaPipe Face Mesh** (Google),
**GhostFaceNets** (HamadYA). This repository redistributes ncnn-converted weights under their
respective upstream licenses; see [`LICENSE.md`](LICENSE.md).