ShiqiYu / ShiqiYu/libfacedetection

how to using onnx model without cv FaceDetectorYN

Open
#368 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
12.8k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

I didn't find relevant code in <opencv2/objdetect/face.hpp>. Could you please explain the meaning of these outputs? I want to integrate them into another platform where I can't use OpenCV

this is face_detection_yunet_2023mar.onnx outputs
0 cls_8: [1, 6400, 1]
1 cls_16: [1, 1600, 1]
2 cls_32: [1, 400, 1]
3 obj_8: [1, 6400, 1]
4 obj_16: [1, 1600, 1]
5 obj_32: [1, 400, 1]
6 bbox_8: [1, 6400, 4]
7 bbox_16: [1, 1600, 4]
8 bbox_32: [1, 400, 4]
9 kps_8: [1, 6400, 10]
10 kps_16: [1, 1600, 10]
11 kps_32: [1, 400, 10]

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with opencv2/objdetect/face.hpp and the face_detection_yunet_2023mar.onnx output names and shapes listed in the issue. Trace how FaceDetectorYN interprets cls, obj, bbox, and kps outputs, then document the meanings needed to integrate the model without OpenCV. Done means the output tensors and their platform-independent interpretation are clearly explained.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
computer-vision
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.