How to build a preprocessing layer with different preprocessing for each feature?

saurabh_tripathy · January 16, 2023, 3:36pm

Hi Team!!

My autoencoder model has numerical, categorical and text features. I am doing a normalization for numerical, custom encoding for categorical and BERT tokenization for text as preprocessing.

I want to build a preprocessing layer with different custom preprocessing for each feature. All the examples on documentation (e.g. https://www.youtube.com/watch?v=GVShIIh3_yE) I see is for uniform attributes like full text or numerical dataset.

Please help me on this.

Topic		Replies	Views
Does text preprocessing or cleaning required for Bert model or others one? General Discussion models , nlp , help_request	3	2152	October 6, 2023
Tensorflow Text Classification with BERT General Discussion docs , models , nlp , model_garden , help_request	2	1994	October 17, 2021
Deploying custom model General Discussion model-code , tfhub	0	121	March 11, 2024
Help with continuous + categorical features General Discussion models , keras , getting_started , help_request	1	1910	September 15, 2022
NLP : Question while working with ALBERT General Discussion nlp , tflite , tfhub , help_request	2	1099	August 4, 2021

How to build a preprocessing layer with different preprocessing for each feature?

Related topics