Comments (9)
from ganet.
from ganet.
回答,
- 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。
- 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.
from ganet.
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.
from ganet.
from ganet.
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
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.
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)
- Why FocalLoss return zero
- FileNotFoundError: [Errno 2] No such file or directory: '/tmp/tmpayfcfwsi/tmpt997zvmj.py'
- python setup.py develop ??
- How can I get the metric results? HOT 2
- RuntimeError: Default process group has not been initialized, please make sure to call init_process_ HOT 3
- mmdet2_25 没有最新的模型吧?
- 运行dist_train.sh报如下错误 HOT 1
- Hi, may I ask in which part of the code the LFA module mentioned in the paper is specifically implemented? HOT 1
- How can I visualize the test results HOT 1
- run test.py get error:KeyError: 'thr' HOT 1
- How can i infer with batch images?
- 在./tools/ganet/speed_test.py里的一些疑惑 HOT 8
- 您好,我可以问一下您mmdet2_25分支中mmcv和mmdet的版本吗? HOT 3
- what's the meaning of cpts_hm, kpts_hm, pts_offset, int_offset
- cuda11.3可以复现GANet这篇论文嘛?!困扰了很久一直有报错哎! HOT 1
- How do I visualize Tusimple test set results? HOT 1
- about LFA module
- 尝试部署该模型到Xaiver,卡在模型转化上了,如果大家有部署相关的经验,欢迎讨论。
- 如何转换onnx文件
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ganet.