-
-
Notifications
You must be signed in to change notification settings - Fork 1.4k
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
[ENH] OS-CNN for time series classification #5828
Comments
Hello @TonyBagnall Sir, Can I be assigned this issue to implement |
hey, has this issue been fixed? |
No, @SABARNO-PRAMANICK, the estimator has not been added yet. I also note, the linked repository does not have a license, so in-principle it has strong copyright on it. We should contact the original author, @Wensi-Tang, whether they are willing to release their code under a permissive license, for integration in |
@fkiraly , since the issue is connected to licensing, can I contribute to this? |
@SABARNO-PRAMANICK, there is existing code here, this looks like a reimplementation: sktime/sktime-dl#111 You could start with the Pr and move it to sktime. |
Hi @fkiraly , I'm working on it, but just to be sure, do you want me to update the already existing code for |
Yes, @SABARNO-PRAMANICK, the way would be to move the files - however there is already Regarding the |
Thank you for the instructions @fkiraly , I need help with understanding a few things so I'll comment it here as well as in the discord thread for better comms;
These are the |
update 2024: as
sktime
now handles backends on estimator level, porting the code with apytorch
dependency is feasible. I.e., atensorflow
rewrite is no longer necessary, as in 2020 insktime-dl
.Original code is in pytorch
Paper: https://arxiv.org/pdf/2002.10061.pdf
Code: https://github.com/Wensi-Tang/OS-CNN/
The text was updated successfully, but these errors were encountered: