Comments (6)
!
That's very interesting. I just stumbled across a similar issue with svm.cpp, but it seems to be the reverse problem there: probability predictions are correct, non-probability predictions are always the same class, but only on certain datasets. I documented it at scikit-learn/scikit-learn#4800
from libsvm.
There is no problem there. Even if the max num is reached, we still
need to return A and B. The if statement prints just a warning message.
mahan66 writes:
If anybody wants to use the probability outputs of the svm, it goes wrong and the
output label is always the same. The problem is in the line 1672:if (iter>=max_iter)
//svm.info("Reaching maximal iterations in two-class probability estimates\n");probAB[0]=A;probAB[1]=B;
As you can see, the next line after the commented part of the if statement will be
fired if the statement in the if is true. Thus, the results are always wrong.Solution
Simply, put comment for the whole if statement.Regards,
Mahmood—
Reply to this email directly or view it on GitHub.*
from libsvm.
I think @mahan66 is pointing out that the comment accidentally changes the meaning. The code should be
if (iter>=max_iter) {
//svm.info("Reaching maximal iterations in two-class probability estimates\n");
}
probAB[0]=A;probAB[1]=B;
from libsvm.
Yep. there is definitely a problem. The compiler interprets this as
if (iter>=max_iter) {
//svm.info("Reaching maximal iterations in two-class probability estimates\n");
probAB[0]=A;
}
probAB[1]=B;
from libsvm.
but right now in svm.java the svm.info statement isn't commented out?
Matthias Richerzhagen writes:
Yep. there is definitely a problem. The compiler interprets this as
if (iter>=max_iter) {
//svm.info("Reaching maximal iterations in two-class probability estimates\n");
probAB[0]=A;
}probAB[1]=B;
—
Reply to this email directly or view it on GitHub.*
from libsvm.
Yes, I checked the current source code now and it seems it is correct here. I don't know what version I was using which somebody had made this change.
from libsvm.
Related Issues (20)
- how can i improve train speed? HOT 1
- why my memory always HOT 1
- Some dataset problem HOT 2
- static library HOT 1
- gridregression.py
- LIBSVM library not found HOT 1
- gridregression.py 出现 RuntimeError: get no mse HOT 2
- Exception Thrown: read access violation HOT 1
- 使用svm-train.exe做回归(regression),参数c与g如何优化 HOT 1
- How to modify SVR loss function? HOT 1
- Accuracies lower than 50% if the random seed is unlucky HOT 8
- one class svm HOT 1
- Questions about the results of libSVM HOT 6
- Questions about probability estimation of one-class svm HOT 4
- 如何调整nu,使训练集的准确率增加? HOT 6
- cannot find -lgcc: No such file or directory HOT 1
- When using svm-scale , missing values come out. HOT 1
- Try using a custom objective function
- MATLAB Crashes when trying to run "svmtrain" on CentOS HOT 2
- Python libsvm 3.33 crashes due to unexpected argument to jit HOT 9
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 libsvm.