Reversible-Instance-Normalization icon indicating copy to clipboard operation
Reversible-Instance-Normalization copied to clipboard

Implementation of RevIN is based on TF2.Keras and PyTorch.

Results 1 Reversible-Instance-Normalization issues
Sort by recently updated
recently updated
newest added

I call your function from: ``` from RevIN import RevIN %load_ext autoreload %autoreload 2 revin_layer = RevIN(2) x=Input(shape=(12,2)) model=revin_layer(x,mode="norm") model2=LSTM(32,return_sequences=False)(model) output_layer=Dense(2)(model2) output_layer1=revin_layer(output_layer,mode="denorm") model1 = Model(inputs=x, outputs=output_layer1) model1.summary() ``` But I...