Downloads · 30 days
0
redrob-labs/redrob-verify-face
redrob-verify-face is a image feature extraction model from redrob-labs. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. It is set up for opencv. The card lists the license as apache-2.0.
Face detection + recognition ONNX weights used by redrob-verify (Redrob verification stack).
Downloads · 30 days
0
Access
Public
Updated Aug 7, 2026
Repo size
38.9 MB
Likes
1
Public
Click a slice to open those files.
.onnx38.9 MB · 100%
From the Hugging Face model README
Face detection + recognition ONNX weights used by redrob-verify (Redrob verification stack).
redrob-labs/redrob-verify-faceservices/face/ in the GitHub repo| File | Model | Role |
|---|---|---|
face_detection_yunet_2023mar.onnx | YuNet | Face detection |
face_recognition_sface_2021dec.onnx | SFace | Face embedding / match |
These are the same Apache-2.0 Zoo artifacts redrob-verify fetches by default.
Republished here so a single Hugging Face download path can bootstrap the stack
without depending on GitHub raw URLs.
Detect faces and compare embeddings for the redrob-verify face service
(face.backend: sface). Typical use: selfie vs ID-document face for KYC-style flows.
# From the redrob-verify checkout (preferred)
./tools/fetch_models.sh
# Or Hub only
huggingface-cli download redrob-labs/redrob-verify-face \
--local-dir models/face
Place files under models/face/ as named above (see config.yaml face.sface.*).
Apache-2.0. Copyright OpenCV / OpenCV Zoo authors. Redrob redistributes unchanged ONNX weights for convenient Hub access; see upstream Zoo notices.
If you use these models, cite OpenCV Zoo (YuNet, SFace) and redrob-verify as appropriate.