search

dfsp-spirit / meshlearn

AI model to predict computationally expensive vertex-wise descriptors like the local gyrification index from the mesh structure.
MIT License
3 stars 0 forks source link

Model: Implement k-fold cross-validation #3

Open dfsp-spirit opened 2 years ago

dfsp-spirit commented 2 years ago

I would suggest k=10.

dfsp-spirit commented 2 years ago

This is now done in the hyperparameter tuning part, but still missing in the standard fitting func (without hp tuning).