kinoml
kinoml copied to clipboard
running notebook with custom loss class for skorch.
Description
This PR focuses on how to use skorch (Pytorch + sklearn) package for training the machine learning models. Advantages: Cool features pre-implemented, e.g.
- Built in cross-validation
- early stopping
- callbacks
- etc.
Todos
- [ ] Include skorch in API
- [x] running example
- [x] custom loss class for pIC50 to enable observation model
Questions
- [ ] Question1
Status
- [ ] Ready to go