Git Product home page Git Product logo

Comments (8)

littletomatodonkey avatar littletomatodonkey commented on June 11, 2024 1

你好,感谢你的关注

  1. 关于检测的问题,因为使用的是超轻量模型,这块anchor的设置其实相对较小,所以检测对于占据图像大部分面积的情况其实处理较差,这块可以参考PaddleDetection在自己的数据集上进行finetune,或者使用更大的模型训练,如果需求很大,我们后续也会考虑提供精度更高的检测模型
  2. 目前该repo中还没有涉及到人脸alignment的步骤,所以你说的这个倾斜的情况下,相似度差异较大的情况是存在的
  3. 两个模型都是从头训练的,参数和训练策略也会造成相似度的差异,不过这块没有定量地评估过
  4. 再次感谢你的关注和使用,效果这块我们会继续优化,你如果有什么需求也欢迎通过issue或者邮件的形式([email protected])联系我~

from insight-face-paddle.

mikeshi80 avatar mikeshi80 commented on June 11, 2024

多谢回复,因为之前的项目,无论是分类,检测,还是OCR,都是使用飞桨的 ,所以在人脸识别上,也希望使用飞桨的平台来完成,以便部署的一致性。我试试看使用OpenCV的人脸检测,加上简单的对齐操作(使用识别出的五点,然后再和给定的标准5点进行一次transform),看看再使用人脸识别后的特征,相似度是否会提高。

from insight-face-paddle.

littletomatodonkey avatar littletomatodonkey commented on June 11, 2024

嗯嗯,我们其实最近也在准备把训练相关的代码合入到insight-face的官方repo中去,可以参考下这个PR:deepinsight/insightface#1652

你可以试下对齐对效果的影响,有效的话欢迎分享或者给我们提PR哈

from insight-face-paddle.

mikeshi80 avatar mikeshi80 commented on June 11, 2024

OK,持续关注

from insight-face-paddle.

mikeshi80 avatar mikeshi80 commented on June 11, 2024

惨,PaddlePaddledlib都用到了OpenMP,所以无法同时在一个项目里使用 ,无法使用dlib来进行人脸检测和对齐……

from insight-face-paddle.

yfq512 avatar yfq512 commented on June 11, 2024

@mikeshi80 大神你好,我想请教一个关于人脸识别的问题:我写了个基于dlib实现人脸识别的项目,当我用uwsgi和Django去部署从而实现多并发时,会报错:from _dlib_pybind11 import * >>> ImportError: libcudnn.so.7: failed to map segment from shared object,而不用uwsgi,仅用Django自带的runserver单线程模式部署就不会报错。
这是dlib的问题么?能否通过修改一些配置来解决这个问题么?

from insight-face-paddle.

mikeshi80 avatar mikeshi80 commented on June 11, 2024

@mikeshi80 大神你好,我想请教一个关于人脸识别的问题:我写了个基于dlib实现人脸识别的项目,当我用uwsgi和Django去部署从而实现多并发时,会报错:from _dlib_pybind11 import * >>> ImportError: libcudnn.so.7: failed to map segment from shared object,而不用uwsgi,仅用Django自带的runserver单线程模式部署就不会报错。
这是dlib的问题么?能否通过修改一些配置来解决这个问题么?

抱歉,才看到,这个问题我也没有头绪,多半是多线程问题。估计要加锁

from insight-face-paddle.

tao2021 avatar tao2021 commented on June 11, 2024

制作索引时,需要多少张图片才有效果,我使用了4张照片来表明是一个人,但是效果完全检测不出来,我想问下,是制作索引的图片太少的原因还是我是用的模型的原因,我i使用的识别模型是mobileface

from insight-face-paddle.

Related Issues (16)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.