Comments (5)
fxwfzsxyq
commented on June 2, 2024
你好！想请问一下，为啥训练出来的模型准确率还可以，而召回率则明显较低
如果你想提高召回率，测试的时候可以适当调低box_thresh
from dbnet-lite.pytorch.
johnnylili
commented on June 2, 2024
你好！想请问一下，为啥训练出来的模型准确率还可以，而召回率则明显较低
如果你想提高召回率，测试的时候可以适当调低box_thresh
你好，你用他提供的预训练模型测试，能达到他的效果吗？
from dbnet-lite.pytorch.
fxwfzsxyq
commented on June 2, 2024
这个我到没试过。
…------------------ 原始邮件 ------------------
发件人: "JohnnyLiLi"<[email protected]>;
发送时间: 2020年9月23日(星期三) 上午10:43
收件人: "BADBADBADBOY/DBnet-lite.pytorch"<[email protected]>;
抄送: "snake"<[email protected]>; "Comment"<[email protected]>;
主题: Re: [BADBADBADBOY/DBnet-lite.pytorch] recall (#8)
你好！想请问一下，为啥训练出来的模型准确率还可以，而召回率则明显较低
如果你想提高召回率，测试的时候可以适当调低box_thresh
你好，你用他提供的预训练模型测试，能达到他的效果吗？
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
from dbnet-lite.pytorch.
johnnylili
commented on June 2, 2024
这个我到没试过。
…
------------------ 原始邮件 ------------------ 发件人: "JohnnyLiLi"<[email protected]>; 发送时间: 2020年9月23日(星期三) 上午10:43 收件人: "BADBADBADBOY/DBnet-lite.pytorch"<[email protected]>; 抄送: "snake"<[email protected]>; "Comment"<[email protected]>; 主题: Re: [BADBADBADBOY/DBnet-lite.pytorch] recall (#8) 你好！想请问一下，为啥训练出来的模型准确率还可以，而召回率则明显较低 如果你想提高召回率，测试的时候可以适当调低box_thresh 你好，你用他提供的预训练模型测试，能达到他的效果吗？ — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
老哥，留个联系方式，一起交流学习
from dbnet-lite.pytorch.
fxwfzsxyq
commented on June 2, 2024
QQ:2441124901
…------------------ 原始邮件 ------------------
发件人: "JohnnyLiLi"<[email protected]>;
发送时间: 2020年9月23日(星期三) 上午10:52
收件人: "BADBADBADBOY/DBnet-lite.pytorch"<[email protected]>;
抄送: "snake"<[email protected]>; "Comment"<[email protected]>;
主题: Re: [BADBADBADBOY/DBnet-lite.pytorch] recall (#8)
这个我到没试过。
…
------------------ 原始邮件 ------------------ 发件人: "JohnnyLiLi"<[email protected]>; 发送时间: 2020年9月23日(星期三) 上午10:43 收件人: "BADBADBADBOY/DBnet-lite.pytorch"<[email protected]>; 抄送: "snake"<[email protected]>; "Comment"<[email protected]>; 主题: Re: [BADBADBADBOY/DBnet-lite.pytorch] recall (#8) 你好！想请问一下，为啥训练出来的模型准确率还可以，而召回率则明显较低 如果你想提高召回率，测试的时候可以适当调低box_thresh 你好，你用他提供的预训练模型测试，能达到他的效果吗？ — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
老哥，留个联系方式，一起交流学习
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
from dbnet-lite.pytorch.
Related Issues (20)
- 稀疏训练之后，Binary Acc和Binary IoU都增加了几个点，正常吗？ HOT 4
- IndexError: list index out of range HOT 15
- Errors in loading state_dict for DBNet HOT 5
- 关于DBhead和FPNhead性能问题？ HOT 3
- 有没有libtorch实现的dbnet推理 HOT 1
- 关于多边形数据的验证问题 HOT 2
- cd models/dcn/ sh make.sh这个必须编译吗？ HOT 1
- 跑几个epoch后，评估指标Binary Acc固定在0.5，正常吗？ HOT 1
- LOSS在不断下降，但是一到验证阶段Recall,p,f1,全部为0 是什么原因？ HOT 4
- pure is wrong HOT 1
- DB模型收敛的慢 HOT 2
- 能增加DB检测后将对应的目标区域裁剪的代码吗
- 用官方放出的权重测试也得不到正确的结果 HOT 2
- 您好，自定义数据集该如何制作呢？ HOT 1
- RuntimeError: Error(s) in loading state_dict for DBNet: HOT 1
- model size(M) HOT 1
- 加载预训练模型 HOT 2
- 训练数据集 HOT 1
- DB.pth.tar哪里可以下载？ HOT 3
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 dbnet-lite.pytorch.