onnx support for Arcface and RetinaFace

See original GitHub issue

Hi, I have read some of your codes and noticed that deploy/test.py with the model named ‘antelope’ is a merge of all your models together, I was wondering if is there separate .onnx files for your models or if they are still going to be still running on Mxnet? since from what I gathered for using models separately for instance Retinaface, the code still imports Mxnet.

Issue Analytics

State:
Created 2 years ago
Comments:5

Top GitHub Comments

2reactions

nttstarcommented, Jun 14, 2021

actually you can call insightface.model_zoo.get_model(‘xxx/scrfd_10g_bnkps.onnx’) which will return a SCRFD instance.

0reactions

nttstarcommented, Jun 14, 2021

We will reorganize our inference library soon and at that time you can see more documentations.

Top Results From Across the Web

face-recognition-resnet100-arcface-onnx

The face-recognition-resnet100-arcface-onnx model is a deep face recognition model with ResNet100 backbone and ArcFace loss. ArcFace is a novel supervisor ...

ONNX Model Zoo: Developing a face recognition application ...

Apache MXNet supports the ONNX format for both import and export. ArcFace Model. The model learns distinctive features of faces and produces ...

ArcFace - a Hugging Face Space by onnx

ArcFace. ArcFace is a CNN based model for face recognition which learns discriminative features of faces and produces embeddings for input face images....

insightface - PyPI

Call Models ----------- The latest insightface libary only supports onnx models. Once you have trained detection or recognition models by PyTorch, ...

Deep Face Recognition with ArcFace in Keras and Python

We will build ArcFace model which got 99.40% accuracy on LFW data set ... Here, retinaface is the cutting-edge face detection technology.