Mr DeepFakes Forums
  • New and improved dark forum theme!
  • Guests can now comment on videos on the tube.
   
Total Likes Received: 1 (0.08 per day | 0.09 percent of total 1060)
(Find All Threads Liked ForFind All Posts Liked For) Total Likes Given: 5 (0.39 per day | 0.47 percent of total 1061)
(Find All Liked ThreadsFind All Liked Posts)

Flame
(DeepFake Producer)
DeepFake Producer

Registration Date: 05-08-2019
Date of Birth: Not Specified
Local Time: 05-21-2019 at 01:20 PM
Status:

Flame's Most Liked Post
Post Subject Numbers of Likes
First fake, a little feedback 1
Thread Subject Forum Name
First fake, a little feedback Discussion
Post Message
First training on intro scene. Only clear faces.
Trained 40-50k with :
 
===== Model summary =====
== Model name: SAE
==
== Current iteration: 0
==
== Model options:
== |== batch_size : 4
== |== sort_by_yaw : False
== |== random_flip : False
== |== resolution : 128
== |== face_type : f
== |== learn_mask : True
== |== optimizer_mode : 1
== |== archi : df
== |== ae_dims : 512
== |== e_ch_dims : 42
== |== d_ch_dims : 21
== |== multiscale_decoder : True
== |== ca_weights : False
== |== pixel_loss : False
== |== face_style_power : 10.0
== |== bg_style_power : 10.0
== |== apply_random_ct : True
== Running on:
== |== [0 : GeForce GTX 1080]
 
Next pushed batch_size to 8 with optimize mode on 2 :
 
== Model options:
== |== batch_size : 8
== |== sort_by_yaw : False
== |== random_flip : False
== |== resolution : 128
== |== face_type : f
== |== learn_mask : True
== |== optimizer_mode : 2
== |== archi : df
== |== ae_dims : 512
== |== e_ch_dims : 42
== |== d_ch_dims : 21
== |== remove_gray_border : False
== |== multiscale_decoder : True
== |== pixel_loss : True
== |== face_style_power : 0.1
== |== bg_style_power : 4.0
== Running on:
== |== [0 : GeForce GTX 1080]
 
Quite nice result. Waited to reach 80k total.
 
Next extracted 2nd scene with more movement and trained with these settings :
 
== Model options:
== |== batch_size : 4
== |== sort_by_yaw : False
== |== random_flip : False
== |== resolution : 128
== |== face_type : f
== |== learn_mask : True
== |== optimizer_mode : 1
== |== archi : df
== |== ae_dims : 512
== |== e_ch_dims : 42
== |== d_ch_dims : 21
== |== multiscale_decoder : True
== |== ca_weights : False
== |== pixel_loss : False
== |== face_style_power : 0.1
== |== bg_style_power : 0.4
== |== apply_random_ct : True
== Running on:
== |== [0 : GeForce GTX 1080]
 
Face looks less merged ? But still decent result. Trained one night about 55k or 60k iterations.
Then pushed batch size to 12 with optimizer mode 2 and following settings :
 
== Model options:
== |== batch_size : 12
== |== sort_by_yaw : False
== |== random_flip : False
== |== resolution : 128
== |== face_type : f
== |== learn_mask : True
== |== optimizer_mode : 2
== |== archi : df
== |== ae_dims : 512
== |== e_ch_dims : 42
== |== d_ch_dims : 21
== |== multiscale_decoder : True
== |== ca_weights : False
== |== pixel_loss : False
== |== face_style_power : 0.1
== |== bg_style_power : 4.0
== |== apply_random_ct : True
== Running on:
== |== [0 : GeForce GTX 1080]
 
Face now looks a little more like dst than src. But it's ok we still recognize src.
Currently at 152k and pretty good result (on preview).
 
Conclusion : Looks like beginning training with face_style_power 10 and bg_style_power 10 is the best choice.
Since decreasing it for 1st pass on second scene produced a less merged face. Also batch_size 12 looks a lot better to me for only a 300ms increase in iterations compared to batch 8. (maybe placebo but ATM seems worth). Also decreased both loss values a much more than batch_size 8.
 Anyway good result at this stage. Probably going to wait 160k and try converting the firsts two scenes to then move to training on more "intense" scenes … Smile
 
Questions : What is exactly the link between batch_size and quality ? What is the link between face_style_power/bg_style_power values and merging of src to dst ? Should I train straight up to batch 12 instead of starting at 4, even if iterations are x2 longer ? Does this workflow looks ok to more experienced deepfakers ?
 
Makes a lot of questions but even with carefully reading documentation I can't really answer them… I can include few previews if needed.

Thanks in advance to deepfakes that will reply to this thread.

fLmmm

Flame's Forum Info
Joined:
05-08-2019
Last Visit:
Today, 01:28 AM
Total Posts:
9 (0.7 posts per day | 0.15 percent of total posts) Find All Posts
Total Threads:
3 (0.23 threads per day | 0.22 percent of total threads) Find All Threads
Time Spent Online:
3 Days, 21 Hours, 7 Minutes
Thanks/Likes:
Given: 5 | Recieved: 1
Members Referred:
0
Flame's Contact Details
Additional Info About Flame
Sex:
Undisclosed