Comments (9)
将他模型中的hm参数改为2,还有数据加载和解码中的num_class改为2就行
…
------------------ 原始邮件 ------------------ 发件人: "ZeroE04/R-CenterNet" @.>; 发送时间: 2021年8月25日(星期三) 上午9:54 @.>; @.@.>; 主题: Re: [ZeroE04/R-CenterNet] 你好,请问这个支持多个类别识别吗? 我拿自己多类别的数据集训练的模型,检测的时候发现他的预测值返回类别都是2.0。如何解决呀? (#3) 你好,请问你问题解决了吗?我这多类别预测也都是2 — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
请问多目标训练后,map是怎么得到的,怎么修改evaluation.py文件呐
from r-centernet.
支持。如果检测多类别,把代码里面num_classes都改成你的类别数目;然后再画框的地方,把画框的颜色自己调整一下,使不同类别颜色不同,我现在只用了一种颜色的框,也就是demo里面红蓝色的框。当然,你打标签的时候就得按照多类别来打
from r-centernet.
你是怎么改修的? cpp 文件的需要修改吗?
from r-centernet.
你是怎么改修的? cpp 文件的需要修改吗?
不需要,修改python中代码
from r-centernet.
你好,请问你问题解决了吗?我这多类别预测也都是2
from r-centernet.
你好,请问你问题解决了吗?我这多类别预测也都是2
from r-centernet.
from r-centernet.
多类别预测是2的原因是predict.py代码有问题,改hm参数、num_class都没有用
from r-centernet.
多类别预测是2的原因是predict.py代码有问题,改hm参数、num_class都没有用
那请问应该怎么调整呢~~
哦 在predict.py里也有两处num_classes 也需要修改
from r-centernet.
Related Issues (20)
- I can't find the detect head. HOT 1
- About variance and standard. HOT 2
- Compare with CenterNet. HOT 1
- 关于类别计算问题 HOT 1
- the differences with centerNet? HOT 1
- 'AttributeError: 'NoneType' object has no attribute 'shape'' HOT 1
- 训练HRSC2016数据集 HOT 13
- angle_loss无法收敛的原因,其他loss均收敛 HOT 1
- x0n= (x0 -x)*cosA -(y0 - y)*sinA + x
- 去掉ang后evalution代码报错 HOT 1
- 数据集中旋转角度都是0,旋转角度loss权重为0,会对神经网络和输出有什么影响? HOT 2
- 角度回归问题 HOT 3
- _topk
- 请问loss的权重分别是:1,0.1,0.1,0.1 这有什么特殊要求吗
- 有关coco_box_to_bbox这个函数的问题
- angle not correct
- angle 回归部分不准确
- 预测宽高不对的问题
- how to execute the pre-trained model ?
- 模型在 4-5 个 epoch 后不再学习 HOT 2
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 r-centernet.