Home Artists Posts Import Register

Content

It's been a little more than two months since I began training my own model for Rife-App, since then it's easily been a model training at least half of each week.

So let's say, 12h of training per day, for 60 days. That give more or less 720h of training.

The hardest part of training a model is that I need around 1:30h to see if a test will work, and sometimes need 8h of training to discover that a change is bad to the model.


While all this study about algorithm and training was very time consuming, it help me learn a lot of new things, stuff that it will help me optimize the memory for all the apps, and perhaps even improve the results.


Anyway, I was able to improve the models in 2.60, now the "Fast" model have more quality and the "Quality" model is lighter and twice as fast.


I'm just finish training the Real Life version of them to release the next update.

Also I'm fixing the reported bugs and improving the memory usage further of the app.


Comments

Anonymous

It's always a time-consuming process if you try to learn something and I'm also sure it's worth it.

Anonymous

Out of curiosity, what hardware are you using to do all this? I imagine it's pretty beefy.

Jelly

Is training something we can help with?

DAINAPP

Sadly no, I need to keep changing the code and looking at the output constantly.