Giter VIP home page Giter VIP logo

Comments (8)

Belinda-great avatar Belinda-great commented on May 21, 2024

12058
18607
12058
18607

from ultra-light-fast-generic-face-detector-1mb.

Linzaer avatar Linzaer commented on May 21, 2024

输入可以设置成320或者更小试下。

from ultra-light-fast-generic-face-detector-1mb.

Belinda-great avatar Belinda-great commented on May 21, 2024

输入可以设置成320或者更小试下。
非常感谢!设置为320完全没问题!

from ultra-light-fast-generic-face-detector-1mb.

summerwbb avatar summerwbb commented on May 21, 2024

你好,请问您出来的结果稳定吗?我现在训练的结果测试图片容易丢帧和回归效果不准确的情况。 @Belinda-great @Linzaer

from ultra-light-fast-generic-face-detector-1mb.

Linzaer avatar Linzaer commented on May 21, 2024

@summerwbb 网络类型?训练输入大小?和提供的预训练模型效果差别大吗?测试时输入多大?如果测试图片人脸很多很小的话,适当减小候选框数值保证有效人脸。

from ultra-light-fast-generic-face-detector-1mb.

summerwbb avatar summerwbb commented on May 21, 2024

我使用的RFB网络训练了一个人头检测模型(使用train_mb_tiny_RFB_fd.sh脚本,只改变了数据),训练和测试输入大小是640,测试时候选框改成了150个,是普通的电影素材。多数是不超过5个。请问我的loss应该降低到大概多少才是收敛了.
image
image
image
image

from ultra-light-fast-generic-face-detector-1mb.

summerwbb avatar summerwbb commented on May 21, 2024

我也同时训练了320 版本,感觉640更适合我的场景。

from ultra-light-fast-generic-face-detector-1mb.

Linzaer avatar Linzaer commented on May 21, 2024

用smooth_l1_loss,320x240训练人脸,200epochs最后大概稳定在2.84左右,640x480大概稳定在2.57左右,仅供参考。你数据集图片数有多少?很大可能和数据集数量和质量有关。你也可以尝试修改下预处理阶段的流程,比如加入Expand方法,扩张原图加强小目标能力,也可以略微修改randomcrop里的纵横比和交并比增强检测大目标能力。当然你也可以略微重复一两个不影响featuremap尺度的block加强网络主干。

from ultra-light-fast-generic-face-detector-1mb.

Related Issues (20)

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.