From 85f2c764fd0192930a64b42e4402eee6fcff3618 Mon Sep 17 00:00:00 2001 From: Jia Guo Date: Fri, 3 May 2019 13:03:55 +0800 Subject: [PATCH] Update README.md --- RetinaFace/README.md | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/RetinaFace/README.md b/RetinaFace/README.md index 45d576c..b971ffe 100644 --- a/RetinaFace/README.md +++ b/RetinaFace/README.md @@ -1,11 +1,31 @@ -### RetinaFace Face Detector +# RetinaFace Face Detector + +## Introduction + +RetinaFace is a robust single stage face detector which initially described as an [arXiv technical report](https://arxiv.org/abs/1905.00641) + + +## Training + +1. Download groundtruth labels from [baiducloud](https://pan.baidu.com/s/1Laby0EctfuJGgGMgRRgykA) or dropbox and organise the dataset directory under ``insightface/RetinaFace/`` as follows(images can be downloaded from WiderFace website directly): +```Shell + data/retinaface/ + train/ + images/ + label.txt + val/ + images/ + label.txt + test/ + images/ + label.txt +``` + +## Testing Please check ``test.py`` for model usage. Pretrained Model: [RetinaFace-R50](https://pan.baidu.com/s/1C6nKq122gJxRhb37vK0_LQ) is a medium size model with ResNet50 backbone. WiderFace validation mAP: Easy 96.5, Medium 95.6, Hard 90.4. It can output face bounding boxes and five landmarks in a single forward pass. -Light weight and large models will be released soon. -![example1](https://github.com/deepinsight/insightface/blob/master/resources/retina_R50_ex1.jpg) -![example2](https://github.com/deepinsight/insightface/blob/master/resources/retina_R50_ex2.jpg)