# Retinaface-caffe

**Repository Path**: yangpei123/Retinaface-caffe

## Basic Information

- **Project Name**: Retinaface-caffe
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-03-12
- **Last Updated**: 2024-03-12

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Add mobilenet v2 0.25 with retinaface-cpp
The following to download all other converted models, mnetv1_25 and R50 are not converted by me.
https://drive.google.com/open?id=1VoABSiHXiVlRCEryKtf3UG_BW9236UUp
# RetinaFace-Cpp
RetinaFace detector with C++

[official RetinaFace](https://github.com/deepinsight/insightface/tree/master/RetinaFace)

I convert [mobilenet-0.25 mxnet model](https://github.com/deepinsight/insightface/issues/669) (trained by [yangfly](https://github.com/yangfly)) to caffe model

* I have checked the output of the two models be the same.

* For same input images, the output of the two detector (python version and cpp version) is same.

* Haven't tested widerface yet, but it is in the plan.

(the code is too simple, only for reference 23333)

**Please replace your own inference code (caffe/ncnn/feather .etc) in the source code**