Lei Xu

Hi, I'm not sure if I understand your plots correctly. Are these plots about the cumulative distribution for synthetic data (generated by GAN) and real (training) data?

For each column, TGAN uses a hidden layer to generate such column. The hidden layers consume a large amount of memory, so it's not easy to adapt TGAN on datasets...

IIUC, you are suggesting that for continuous column, first generate the cluster id using GAN, and then sample a value from the distribution of such cluster. But the distribution within...

Can you explain a little bit more? thanks.

Please follow README, rename files and put them into the correct directory.

I'm not sure what happened. Can you show me the command you use and more error information? The problem may also be caused by Windows which uses \ in path...

I think the problem is the backward slash on Windows against forward slash on Unix like systems. You may try the code on a Linux machine (or a virtual machine).