phygnn
phygnn copied to clipboard
NREL
physics-guided neural networks (phygnn)
As of scikit-learn version 1.2 the `sparse` parameter for `OneHotEncoder` has been renamed to `sparse_output`. Update name and pin scikit-learn >= 1.2 or pin < 1.2?
Added recursive layer initialization in `HiddenLayers` and `Sup3rObsModel` which can be built from nested hidden layers in a config, and also ingest multiple obs features / exo features.
**Why this feature is necessary:** Skip connection layers currently add their content to the next skip location to create a resnet architecture. Concatenation instead of addition would enable u-net architecture....
How would we feel about adding an issue to deprecate the random forest stuff? I don't think we ever use this. I think we built this originally when testing rf...
Python 3.12+ requires Tensorflow 2.16+, which requires Keras 3. Keras 3 implemented a complete rewrite enabling "multi-framework machine learning", using any of JAX, TensorFlow, and PyTorch and moving between them...
Small fix for idw_fill with 4D models. Deprecating random forest code