search

rasbt / deeplearning-models

A collection of various deep learning architectures, models, and tips
MIT License
16.76k stars 4.02k forks source link

Question about conditional autoencoder #58

Closed sparshgarg23 closed 2 years ago

sparshgarg23 commented 2 years ago

Hi sebastian, I have some questions about CVAE,hope you can help me understand So,rather than training CVAE on images,I am trying to train it on a list of numpy arrays,each array contains 45 parameters. As for my condition variable it consists of 33 parameters . in all the training X's total size is 1500x43 and the condition variable's size is 33x3 Any ideas on what modifications I can do to run CVAE on my example.Basically I am trying to generate new values for each of the 45 parameters given the values in the condition variable. Also,will a CVAE be a suitable choice for my case.

rasbt commented 2 years ago

From my experience, running VAEs on non-image data is notoriously difficult. The reason is that it is very hard to check whether it creates sensible results. Sure, you can look at the loss values, but it is still hard to tell compared to looking at image quality.

sparshgarg23 commented 2 years ago

Thanks that sort of confirmed my earlier suspicion.