0
$\begingroup$

I am trying to train on some 1 dimensional data (675 samples, its very expensive to get more) and trying to match the distribution seen here: enter image description here

There are labels from 1-3 as to associated with the noise. After 2000, epochs, I generate 675 samples and the distribution doesn't look too swell. In addition, there is a odd spacing at $x = 1$ between [0.3, 0.5] as seen here:

enter image description here

Here are the losses:

enter image description here enter image description here

Architecture (Top is discm, Bottom is Gen): enter image description here

Any ideas :/ ?

Improve this question
$\endgroup$

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.