insightface/deploy at 5ca3f995d58f13da8589669ac3ca4f01a107c29c - insightface - Gitea: Git with a cup of tea

ZF/insightface

mirror of https://github.com/deepinsight/insightface.git synced 2025-12-30 08:02:27 +00:00

Files

History

Jia Guo bf306e944c Update README.md

2021-05-04 22:49:44 +08:00

..

add deployment

2018-01-26 13:07:00 +08:00

convert_onnx.py

refine repo structure

2020-11-06 13:59:21 +08:00

face_model.py

use retinaface in deploy/face_model

2020-11-07 13:22:05 +08:00

model_slim.py

refine repo structure

2020-11-06 13:59:21 +08:00

mtcnn_detector.py

use retinaface in deploy/face_model

2020-11-07 13:22:05 +08:00

mxnet_to_ort.py

code of pip insightface==0.2

2021-05-04 16:17:50 +08:00

README.md

Update README.md

2021-05-04 22:49:44 +08:00

test.py

insightface-pip example

2021-05-04 22:38:07 +08:00

Tom_Hanks_54745.png

new age and gender val

2018-05-18 10:41:21 +08:00

README.md

InsightFace deployment README

For insightface pip-package <= 0.1.5, we use MXNet as inference backend, please download all models from onedrive, and put them all under ~/.insightface/models/ directory.

Starting from insightface>=0.2, we use onnxruntime as inference backend, please download our antelope model release from onedrive, and put it under ~/.insightface/models/, so there're onnx models at ~/.insightface/models/antelope/*.onnx.

The antelope model release contains ResNet100@Glint360K recognition model and SCRFD-10GF detection model. Please check test.py for detail.