New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implementing Simple Radial Basis Function Layer #2261
Conversation
This code touches the ANN code, and there was recently a big refactoring of the ANN code in #2259, so be sure to merge the master branch into your branch here to make sure that nothing will fail if this PR is merged. 👍 (I'm pasting this message into all possibly relevant PRs.) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There are a lot of style issues, please use the style checks and fix them all
src/mlpack/methods/ann/activation_functions/gaussian_function.hpp
Outdated
Show resolved
Hide resolved
src/mlpack/methods/ann/activation_functions/gaussian_function.hpp
Outdated
Show resolved
Hide resolved
This issue has been automatically marked as stale because it has not had any recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions! 👍 |
keep open |
fb61043
to
3def59d
Compare
c6a8f87
to
4ed29cf
Compare
Also could you give me a link/reference to an implementation which you are referring to implement this. In most implementation I see the centres and scaling factors are being trained as well. |
Alright, so I do not think that we need the |
I will try and get back to you @saksham189 |
Hey @himanshupathak21061998 I think the work here is almost complete. |
typename Activation> | ||
RBF<InputDataType, OutputDataType, Activation>::RBF() : | ||
inSize(0), | ||
outSize(0) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can you initialise betas and sigmas to 0 here. I think that should fix the static code analysis check.
47b544c
to
151fc51
Compare
Hey Himanshu did you try running the test locally with random seed? |
Yup, @saksham189 already did see the comment above
|
alright great! can you run the current test locally multiple times and see if it continues to pass? |
Sorry for the late reply actually I have to rebuild the project which took some time I ran the tests 20 times and with no failure. I will start working on SVM from tommorow. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think this looks good to merge if you just make the 2 minor fixes :)
src/mlpack/methods/ann/activation_functions/gaussian_function.hpp
Outdated
Show resolved
Hide resolved
src/mlpack/methods/ann/activation_functions/gaussian_function.hpp
Outdated
Show resolved
Hide resolved
Co-authored-by: saksham189 <7020962+saksham189@users.noreply.github.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the work on this!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Second approval provided automatically after 24 hours. 👍
Thanks again @himanshupathak21061998 ! |
Thanks for merging @saksham189 |
Hey @zoq I am trying to add simple RBF network in mlpack. Task needed to be completed are as follows. It's not completed yet I will try to complete it. Please suggest if you have any inputs for this.