Better training history

What’s Changed

• Gb/better history (#22) @grantbuster

Release for DOI

What’s Changed

• incremented veresion for doi release (#21) @grantbuster

GAN implementation

What’s Changed

Breaking change: switched position of y_true and y_predicted in p_fun to match the keras metrics methods.

• Gb/gan (#20) @grantbuster

Bug Fixes

• add shuffle to model interfaces (#19) @MRossol

Bug fix for dropout layers with phygnn

What’s Changed

phygnn wasnt executing dropout layers correctly. The Dropout layer object needed a boolean flag to know if it was training or not. Fixed with additional tests.

• Gb/dropout bug (#18) @grantbuster

Bug fix for saving phygnn model with tensorflow 2.4.0

What’s Changed

• phygnn save() to now save optimizer config dict instead of optimizer … (#17) @grantbuster

phygnn model interface fixes and better one hot encoding

What’s Changed

• Ohe norm fix (#15) @MRossol
• Allow changing loss weights on phygnn model interface (#13) @mikebannis
• Allow RNG seeding before model initiation (#12) @mikebannis

Features

• add one_hot_categories to model handlers (#14) @MRossol

Bug Fixes

• add one_hot_categories to model handlers (#14) @MRossol

Added phygnn model as input to p_fun

What’s Changed

Added phygnn model as input to p_fun. This will enable custom loss functions that can evaluate predictions of the model at the current moment in training.

Added dummy pfun for user example.

• Added phygnn model instance as input arg to p_fun. Added dummy exaple (#11) @grantbuster

add PhygnnModel interface

What’s Changed

Features

• PhygnnModel (#10) @MRossol

Bug Fixes

• Gb/batch norm (#9) @grantbuster
• Gb/loss metric bugs (#8) @grantbuster

Normalization to PreProcess

What’s Changed

• Move normalize and unnormalize methods from BaseMethod to PreProcess
• Add check for stdev values of ~0 and replace with 1s

Features

• move normalization methods to PreProcessing (#7) @MRossol

Model Interfaces added

What’s Changed

• model_interfaces sub-package added with interfaces for TfModel and RandomForestModel
• utilities moved to utilities sub-package

Features

• Model Interfaces (#6) @MRossol