Mr DeepFakes Forums
  • New and improved dark forum theme!
  • Guests can now comment on videos on the tube.
   
Total Likes Received: 1 (0.01 per day | 0.07 percent of total 1495)
(Find All Threads Liked ForFind All Posts Liked For) Total Likes Given: 18 (0.15 per day | 1.2 percent of total 1496)
(Find All Liked ThreadsFind All Liked Posts)

xomnow
(LightFaker)
LightFaker

Registration Date: 03-23-2019
Date of Birth: Not Specified
Local Time: 07-21-2019 at 06:14 PM
Status:

xomnow's Most Liked Post
Post Subject Numbers of Likes
RE: DeepFaceLab Explained and Usage Tutorial 1
Thread Subject Forum Name
DeepFaceLab Explained and Usage Tutorial Guides
Post Message
Is there something new with the multiscale decoder with 4.20?

Couldn't get training to start with it on, but no issue with it off.

With it on:

===== Model summary =====
== Model name: SAE
==
== Current iteration: 0
==
== Model options:
== |== batch_size : 4
== |== sort_by_yaw : False
== |== random_flip : True
== |== resolution : 128
== |== face_type : f
== |== learn_mask : True
== |== optimizer_mode : 1
== |== archi : df
== |== ae_dims : 512
== |== e_ch_dims : 42
== |== d_ch_dims : 21
== |== remove_gray_border : False
== |== multiscale_decoder : True
== |== pixel_loss : False
== |== face_style_power : 0.0
== |== bg_style_power : 0.0
== Running on:
== |== [0 : GeForce RTX 2070 with Max-Q Design]
=========================
Starting. Press "Enter" to stop training and save model.
[12:59:40][#000001][18.80s][15.0361][9.8411]
Error: operands could not be broadcast together with shapes (128,128,3) (64,64,3)
Traceback (most recent call last):
File "D:\Deep Learning Face Swap\DeepFaceLabCUDA10.1AVX 4 20 19\_internal\DeepFaceLab\mainscripts\Trainer.py", line 136, in trainerThread
send_preview()
File "D:\Deep Learning Face Swap\DeepFaceLabCUDA10.1AVX 4 20 19\_internal\DeepFaceLab\mainscripts\Trainer.py", line 59, in send_preview
previews = model.get_previews()
File "D:\Deep Learning Face Swap\DeepFaceLabCUDA10.1AVX 4 20 19\_internal\DeepFaceLab\models\ModelBase.py", line 270, in get_previews
return self.onGetPreview ( self.last_sample )
File "D:\Deep Learning Face Swap\DeepFaceLabCUDA10.1AVX 4 20 19\_internal\DeepFaceLab\models\Model_SAE\Model.py", line 411, in onGetPreview
ar = S[i]*test_S_m[i], SS[i], D[i]*test_D_m[i], DD[i]*DDM[i], SD[i]*(DDM[i]*SDM[i])
ValueError: operands could not be broadcast together with shapes (128,128,3) (64,64,3)
Done.

xomnow's Forum Info
Joined:
03-23-2019
Last Visit:
Yesterday, 05:16 PM
Total Posts:
11 (0.09 posts per day | 0.13 percent of total posts) Find All Posts
Total Threads:
0 (0 threads per day | 0 percent of total threads) Find All Threads
Time Spent Online:
1 Day, 3 Hours, 51 Minutes
Thanks/Likes:
Given: 18 | Recieved: 1
Members Referred:
0
xomnow's Contact Details