MrDeepFakes Forums

Some content may not be available to Guests. Consider registering an account to enjoy unrestricted access to guides, support and tools

  • We are looking for community members who are intested in helping out. See our HELP WANTED post.

How Does Training Work?

LCC

DF Pleb
For each destination picture, does the trainer only use source pictures with a similar face angle? 

Or is a free-for-all, with any image being chosen?
 

VirginBoI

DF Pleb
LCC said:
For each destination picture, does the trainer only use source pictures with a similar face angle? 

Or is a free-for-all, with any image being chosen?

As per what I have observed  if there are a face similar in angle in src and dst then it is pseudo independent of that. Basically it chooses pictures of both faces  and  learns to draw it simultaneously  . later it just switches to creating a src face where it should create dst .

Kind of you learn two languages (src and dst facesets) and all alphabets of them  ( here faces) and later just translate what written in second language sentence (dst faces) into your learned first language sentence making use of its alphabets which closely resembles to the meaning to what written in second .

So yes its pseudo independent as if there are no faces of similar angle in src like in dst then It will simply not know how to translate that dst face specific angle into prediction. Like there is no alphabet equivalent of that second language (dst) alphabet in first
 

LCC

DF Pleb
VirginBoI said:
LCC said:
For each destination picture, does the trainer only use source pictures with a similar face angle? 

Or is a free-for-all, with any image being chosen?

As per what I have observed  if there are a face similar in angle in src and dst then it is pseudo independent of that. Basically it chooses pictures of both faces  and  learns to draw it simultaneously  . later it just switches to creating a src face where it should create dst .

Kind of you learn two languages (src and dst facesets) and all alphabets of them  ( here faces) and later just translate what written in second language sentence (dst faces) into your learned first language sentence making use of its alphabets which closely resembles to the meaning to what written in second .

So yes its pseudo independent as if there are no faces of similar angle in src like in dst then It will simply not know how to translate that dst face specific angle into prediction. Like there is no alphabet equivalent of that second language (dst) alphabet in first

Gotcha, thanks!
 
Top