Implementation kNN loss and created a test notebook

khalil-research / PyEPO

A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming

MIT License

429 stars 56 forks source link

Implementation kNN loss and created a test notebook #31

Closed NoahJSchutte closed 3 months ago

NoahJSchutte commented 4 months ago

I created a new class called optDatasetKNN in dataset.py that can be used to use the kNN loss. Additionally I tested the class in a notebook that is a copy of notebook 03 Training and Testing. For more information see my email.

LucasBoTang commented 4 months ago

Hi @NoahJSchutte ,

Thank you for the pull request and congratulations on your work being accepted at IJCAI! I'm looking forward to diving into the details of your kNN loss implementation. I plan to review it thoroughly by next week and will provide feedback or any necessary suggestions then.

Best regards, Bo

LucasBoTang commented 3 months ago

Hi @NoahJSchutte ,

I have successfully merged the changes into the main branch. The code for the optDatasetKNN class has been optimized and refined.