Pytorch_Retinaface

Pytorch_Retinaface copied to clipboard

Hey thanks for making this project, It might be a good idea to add weights into a Github release. This way it is easier to automate the download process. Thanks

Nintorac

您好，我在您的代码基础上添加了姿态分支，口罩分支暂时还未进行。精度93.7%，下降1个百分点，我在考虑使用mosaic数据增强，但像仿射变换等操作我都放弃了使用，请问你有什么建议么？ 此外，您的代码对于空标注的图像好像不能处理！那么为什么也要返回空的annotations呢？  

gengyanlei


FlyEgle

FlyEgle

How to get the camera parameters

3

Hi, thanks for your excellent work, i run the detect.py and get the box and landmark result. However, i want to get the camera parameters ,like camera location,camera pose and...

hengshan123

Input is not normalized to [-1, 1]

8

Hi, Why the input is not normalized to -1.~1. ? ``` img -= (104, 117, 123) ```

eeewhe

evaluation.py error

6

hi, thanks for you share. First i run this command: python setup.py build_ext --inplace and then i run: **python evaluation.py -p widerface_txt/ -g ground_truth/** i get error like this: ImportError:...

wanglaotou

RetinaFace Anti Cov Face Detector

3

@biubug6, Thanks for your great repo. Do you have any plan for implement a PyTorch implementation of **RetinaFace Anti Cov Face Detector (Face Mask Detection - for Covid)** base on...

ahkarami

请问为什么仅仅在三个特征图上做检测，而不是原论文中的5个？

2

RT

westnight

请问，在将检测到的人脸框输入到人脸识别模块之前，是不是首先要做一次人脸对齐映射？

1

klq-Y