Downloads · 30 days
0
face-pipeline-ncnn
lightcella/face-pipeline-ncnn
face-pipeline-ncnn is a image feature extraction model from lightcella. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. The card lists the license as other.
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 again…
Access
Public
Updated Jul 11, 2026
Repo size
13.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin13.1 MB · 99%
At a glance
- Task
- Image Feature Extraction
- License
- other
- Access
- Public
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026
- SHA
- babe70ce
Model card
From the Hugging Face model README
Lightcella Face Models (ncnn)
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 | 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 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).
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.
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.
- Task
- Image Feature Extraction
- License
- other
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026