LSTM - Scaling training data MinMaxScaler Flux alternative

I try to build a model of a dynamic system very similar to Using PyTorch based LSTM to model nonlinear dynamic systems using Flux in Julia. I need to scale the train/test date to (-1,1) but I didn’t find a scaling function similar to PyTorch MinMaxScaler(feature_range=(-1, 1)) . I believe that there is a simple way to scale date in Julia but I don’t know how :slightly_smiling_face:.

Thanks in advance for the hints :+1:


TableTransforms.jl is a general solution not related to Flux.jl. Maybe it can be useful to you.

1 Like

GitHub - invenia/FeatureTransforms.jl: Transformations for performing feature engineering in machine learning applications is a similar package if you want to work on arrays directly.