视网膜检测物体检测器 介绍 RetinaDetector是基于RetinaFace修改过的检测方法的,原论文是一种实用的单级面部检测器,最初在 数据 如下组织数据集目录: data/retinaface/ train/ images/ label.txt val/ images/ label.txt test/ images/ label.txt 安装 安装具有GPU支持的MXNet。 如果使用基于DCN的主干,请从安装 Convolution V2运算符。 键入make来构建cxx工具。 训练 请检查train.py进行培训。 将rcnn/sample_config.py复制到rcnn/config.py 为了获得更好的训练效果,可针对性的修改一些参数,如下: config.TRA
1
http://vis-www.cs.umass.edu/lfw/index.html#download
2021-06-10 13:06:57 99.53MB lfw
1
提供了一个人脸视频,训练好的人脸检测模型和人脸关键点检测模型,以及一个人脸关键点检测的工程
2021-04-23 14:13:27 167.61MB face alignme
1
人脸检测face-alignment内置模型sfd_detector。原始下载链接https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth。
2021-03-23 13:09:46 85.68MB s3fd face alignment
1
Regression-based face alignment approach is fast and accurate but is always limited by the initial face. Aim at limitation of initialization in regression methods, this paper presents a novel two-stage framework named salient-points-guided face alignment. In rst stage, we use cascade regression framework to train a salient points (eye centers, nose, mouth corners) localization model. Then the salient points information is used as a guidance for search- ing the similar faces from training set. I
2021-02-07 12:05:58 2.3MB Face alignment · Salient
1