Confusion on Extract Instruction regarding N=1

Extracting faces for training and converting
Forum rules
Read the FAQs and search the forum before posting a new topic.

Please mark any answers that fixed your problems so others can find the solutions.
Post Reply
User avatar
iguana314
Posts: 3
Joined: Thu Sep 10, 2020 2:05 pm

Confusion on Extract Instruction regarding N=1

Post by iguana314 »

Hi,

I am very new to faceswap so apologies if this is a trivial question. I have done a bunch of ML in the past so I am familiar with the general flow.

My question is related specifically to this line in the "Extract" tutorial:
"If you are extracting for convert, or you are extracting for convert AND will be using some of the faces for training, then leave this on 1 (i.e. extract from every frame)".

As I understand it, I need to extract both Video A (the face I am removing) and Video B (the face I am inserting). However, what does it mean in the above if I am "extracting for convert and using some of the faces for training"?

Logically, it seems to me that for Video A I need to use N=1 because I need to cut the face out for every frame. For Video B, Should I use N = 12 or N= 15 then? As on a 60 FPS video I don't need every single frame? Thanks in advance for your help!

User avatar
bryanlyon
Site Admin
Posts: 473
Joined: Fri Jul 12, 2019 12:49 am
Answers: 39
Location: San Francisco
Has thanked: 3 times
Been thanked: 114 times
Contact:

Re: Confusion on Extract Instruction regarding N=1

Post by bryanlyon »

Yes, you're right. Use EEN=1 for the video you're planning on extracting and EEN of a higher number for any other videos.

Post Reply