Giter Club home page Giter Club logo

Comments (16)

Linzaer avatar Linzaer commented on May 13, 2024 1

@Jay-Liu 没没没,我也在学习中,也都是在其他大佬的肩膀上玩,开源就是和大家互相交流学习哈~

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

Linzaer avatar Linzaer commented on May 13, 2024

用640x480输入推理

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

Linzaer avatar Linzaer commented on May 13, 2024

我测的是固定中小输入下的精度,现实场景一般都是固定大小输入,比如320或者640

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

wangergou135 avatar wangergou135 commented on May 13, 2024

@Linzaer
wider face测试的图片和./imgs目录下的图片不是固定输入大小,detect_img.py run_video_face_detect.py里并没有resize操作而是直接读取图片再predict。
所以我不太明白的是,用640*480的输入推理是怎么在wider face和./imgs目录下的图片进行推理的?

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

Linzaer avatar Linzaer commented on May 13, 2024

@yushanhu12345 有resize的哦,在PredictionTransform里,封装到预处理里了

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

wangergou135 avatar wangergou135 commented on May 13, 2024

@Linzaer
哦,明白了!
难怪很多大图识别效果不好,准备尝试一下把大图crop出几个vga的tile分别predict,效果应该会好不少

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

Linzaer avatar Linzaer commented on May 13, 2024

@yushanhu12345 可以尝试修改图片输入大小,比如detect_imgs.py里面修改开头第11行的input_img_size,可以适当加大,默认提供(128/160/320/480/640/1280)这几个输入可选。同时如果你想识别大图小人脸场景,建议使用 Mb_Tiny_RFB_FD_train_input_640.pth这个模型,是用640x480训练的,更加适合大分辨率输入,误报低。

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

wangergou135 avatar wangergou135 commented on May 13, 2024

@Linzaer
自己训练的一些模型和你这个模型,好像都有个问题,就是用大分辨率训练的模型,误检少,对小脸的recall低,
用小分辨率训练的模型,误检多,对小脸的recall高。
刚用Mb_Tiny_RFB_FD_train_input_320.pth和Mb_Tiny_RFB_FD_train_input_640.pth测试过,其他条件都一样(输入640×480的图片,从原图上crop, threshold=0.3)

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

Linzaer avatar Linzaer commented on May 13, 2024

@yushanhu12345 一般来说是都这样的,应该是不同大小输入训练的感受野对应原图大小区域的问题。

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

Jay-Liu avatar Jay-Liu commented on May 13, 2024

来围观一下大神@-@

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

leiyu1980 avatar leiyu1980 commented on May 13, 2024

可以说说训练这个检测器的心得嘛。效果确实不错,速度也快。

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

Linzaer avatar Linzaer commented on May 13, 2024

@leiyu1980 调参压榨结构,炼丹

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

nttstar avatar nttstar commented on May 13, 2024

问一下anchor是如何设置的?

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

Linzaer avatar Linzaer commented on May 13, 2024

@nttstar 大佬好~anchor设计参考了于老师的libfacedetection,四分支3/2/2/3个数配比正方形,加强小人脸和大人脸能力。320x240输入得到的四个feature尺寸(40,20,10,5),然后8*n关系设置大小,每层2倍增加。我也用check_gt_box.py得到训练集的尺寸分布调整过数值,效果差不多。

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

tfygg avatar tfygg commented on May 13, 2024

有个疑惑,如上代码是crop出一个h=w的正方形图像,数据扩展也没有padding的过程,那这样在直接resize后人脸会有形变呀。

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

Linzaer avatar Linzaer commented on May 13, 2024

@tfygg 你好,由于人脸主要贴近正方形,所以选的纵横比是1,但是能等于1 的时候几率是非常低的,几乎不会进入下面的randomcrop,所以绝大部分数据几乎是原图,而且如果等于1,resize一定的形变也是可以接受的,因为即使有Expand,当randomcrop出小区域的不同比例的时候,resize之后也是会形变的。由于模型比较小,所以没采用Expand去扩展原图来加强小人脸检出能力,测试调参发现去掉Expand效果会好点,可能是原本数据集的小人脸就已经足够去拟合了。不过这是我的测试结果和想法,你也可以去调参试试~期待更好的结果。

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.