How can I ask a conditional auto encoder to put more emphasis on the condition?

Here's an example of what I'm testing on. I have the mnist digits data and I randomly add a random number from 1 to 10 to each digit and divide it by 11. I do this because I wanted to test out the results of the conditional auto encoder.

I use the means of each digit as the condition and set up a keras conditional auto encoder. Just to visualize it better, I set up the latent dimension to be …

data deeplearning encoder example mnist random test testing