Comments (7)
@KevinTang29 Maybe Focal loss is an available method to solve the imbalance between the background class and other classes in training. Please have a try, and use "SigmoidFocalLoss" instead of "CrossEntropy" for multi-classes in the LI_Fusion_with_attention_use_ce_loss.yaml. Good luck to you!
from epnet.
@happinesslz Thank you very much for your advice. It seems that the original "SigmoidFocalLoss" can only be applied in binary classification, and I tried to change it to focal loss under multiple classification and trained with the focal loss. However, the problem still exists. Maybe the parameter alpha and gamma need to be tuned under multiple classification? In addition, I tried to increase the cross entropy weights of the object classes
to [1.0, 2.0, 2.0, 2.0], and also decrease the roi number in training
to 32 and trained with CE loss again, and the result is better. (though still not right, something like the classfication score changed from [0.9, 0.08, 0.01, 0.01] to [0.7, 0.25, 0.03, 0.02] if the roi is actually of class 1). Is this another possible way to solve the problem?
from epnet.
Did you make it work for multiclass-Epnet?
from epnet.
Did you make it work for multiclass-Epnet?
I just trained the model with CE loss with class weights. I set the model to detect four classes ['Car', 'Pedestrian', 'Cyclist', 'Truck'] and set the corresponding weights to be [1.0, 3.0, 6.0, 6.0, 12.0] (the first weight is of background class). The evaluation results seemed acceptable, though not good enough. Maybe the weights and other parameters need to be tuned further.
from epnet.
from epnet.
I have finished , can you show your mail to me ?and we can talk deeper ------------------ 原始邮件 ------------------ 发件人: "happinesslz/EPNet" <[email protected]>; 发送时间: 2021年1月28日(星期四) 下午4:03 收件人: "happinesslz/EPNet"<[email protected]>; 抄送: "何必歇斯底里"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [happinesslz/EPNet] Detecting multiple classes (#8) Did you make it work for multiclass-Epnet? I just trained the model with CE loss with class weights. I set the model to detect four classes ['Car', 'Pedestrian', 'Cyclist', 'Truck'] and set the corresponding weights to be [1.0, 3.0, 6.0, 6.0, 12.0] (the first weight is of background class). The evaluation results seemed acceptable, though not good enough. Maybe the weights and other parameters need to be tuned further. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
I would like to know how you did. My Email is [email protected]
from epnet.
I have finished , can you show your mail to me ?and we can talk deeper ------------------ 原始邮件 ------------------ 发件人: "happinesslz/EPNet" <[email protected]>; 发送时间: 2021年1月28日(星期四) 下午4:03 收件人: "happinesslz/EPNet"<[email protected]>; 抄送: "何必歇斯底里"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [happinesslz/EPNet] Detecting multiple classes (#8) Did you make it work for multiclass-Epnet? I just trained the model with CE loss with class weights. I set the model to detect four classes ['Car', 'Pedestrian', 'Cyclist', 'Truck'] and set the corresponding weights to be [1.0, 3.0, 6.0, 6.0, 12.0] (the first weight is of background class). The evaluation results seemed acceptable, though not good enough. Maybe the weights and other parameters need to be tuned further. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
Hello @Benedict0819 , I also want to achevice the multi-clas on EPNet, could you please share your code about multi-class to me?
My email address is [email protected]
Thank you very much!
from epnet.
Related Issues (20)
- 0 mAP on Pedestrian class HOT 12
- cannot find your "w" code HOT 1
- How to visualize the Image Feature on Fig. 4?
- about SUNRGBD HOT 1
- why use tools/run_eval_model.sh and github afford model can't get same AP? HOT 2
- Is there an error in the directory where the data is loaded?The data organization structure is Kitti / object / training /, but the path loaded in the code class kittircnndataset (kittidataset) is Kitti / Aug_ scene/training/aug_ label
- train the model then core dumped
- When can we expect the release of EPNet++? HOT 1
- How to run the test mdoe? HOT 3
- about data augmentation HOT 2
- When can you release EPNet++ code?
- AssertionError: Caught AssertionError in replica 1 on device 1.
- Some trouble when training EPNet on 3090 HOT 1
- Data processing
- cant compile the bash script. HOT 2
- A problem during the training
- RuntimeError: Error compiling objects for extension HOT 3
- question about the scores
- CE_lOSS
- sh build_and_install.sh 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 epnet.