Code Monkey home page Code Monkey logo

Comments (9)

Onehundred0906 avatar Onehundred0906 commented on September 13, 2024

@Wolfwjs

from ganet.

Onehundred0906 avatar Onehundred0906 commented on September 13, 2024

@spyflying

from ganet.

hrz2000 avatar hrz2000 commented on September 13, 2024

回答,

  1. coord_mat是根据图像尺寸构造的每个点的2d坐标,加上pts_offsets表示的是从每个点出发预测的起始点坐标,(网络回归的应该就是关键点相对于起始点的偏移量,说法是对的,在预测的时候我们不知道谁是关键点,就预测所有点相对于起始点的偏移量),然后由int_offset弥补预测数值误差,后处理的时候才找出其中的关键点。
  2. tools/speed_test.py文件在编写的时候没有和模型兼容,应该在forward_test传入img_metas的时候,套一个列表model.forward_test(x,[img_metas])。img_metas在传入forward_train\forward_test的时候都是一个列表,这是mmdet的特性,列表里面是本批batch的各个元素的字典,包含了img_shape等各种keys。最后一张图只是用于测试时间的时候,这个时候不需要后处理,就没有包含太多的keys,具体在训练时候其中包含哪些keys,可以从dataset文件里面找到

from ganet.

Onehundred0906 avatar Onehundred0906 commented on September 13, 2024

from ganet.

hrz2000 avatar hrz2000 commented on September 13, 2024

不好意思回复稍晚,刚注意到邮件。
是的,keypointhead的输出概率越大就更可能是关键点,这是因为我们给到他的监督信号是用gt关键点做的heatmap,上次我说的“后处理的时候才找出其中的关键点”不是很准确,我想表达的是问题当中的“起始点”是通过加偏移量什么的后处理获得的(起始点是根据关键点+预测的偏移量进行聚类后处理得到的),关键点通过阈值就可以算出来(也是后处理)。

from ganet.

Onehundred0906 avatar Onehundred0906 commented on September 13, 2024

from ganet.

Onehundred0906 avatar Onehundred0906 commented on September 13, 2024
image

from ganet.

hrz2000 avatar hrz2000 commented on September 13, 2024

时间稍微有点长了,记忆已经开始模糊不清了,也已经错乱了😭
“这个root_center_arr这个变量是什么呢?我的理解是:我看这个变量的筛选条件就是置信度要大于0.3,并且x的offset要小于1,这不就是起始点了吗?”,不是,这个只是初步筛选,符合这些条件才有可能是关键点,后面还会在
image
后处理,里面涉及的后处理逻辑论文里面应该有讲
“按您说的“coord_mat是根据图像尺寸构造的每个点的2d坐标,加上pts_offsets表示的是从每个点出发预测的起始点坐标”,您预测的这个pts_offsets是相对于网格点的偏差不是相对于起始点的偏差?” 我们说的是一个东西,我的意思是预测是起始点相对于这个grid的偏移,根据这个偏移预测,再加上这个grid的坐标就可以得到其预测的起始点是谁,这点是比较绕的,可以先看论文理一理思路再看代码

from ganet.

Onehundred0906 avatar Onehundred0906 commented on September 13, 2024

好的 谢谢你哈 又看了一下论文 现在基本都懂了

from ganet.

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.