Generative Adversarial Network Action Set
The tabularGanTrain Action
The tabularGanTrain action trains a correlation-preserving conditional tabular generative adversarial network (CPCTGAN) model on tabular data in SAS Viya. The action implements the CPCTGAN model by using the PyTorch library.
The tabularGanTrain action has the following features:
It generates synthetic tabular data that preserve the pairwise correlations between variables from the original data.
It supports multithreaded training on one graphics processing unit (GPU) device.
Last updated: September 15, 2022