DeepFaceLab icon indicating copy to clipboard operation
DeepFaceLab copied to clipboard

Training Fails using SAEHD [it doesn`t load faces from data_dst

Open Arsenii101 opened this issue 2 years ago • 2 comments

During 6th step "train SAEHD" the programm didn`t load any packed faces and just stopped. After reboot it loaded packed faces, but still nothing happens. Can anyone help please with that problem?

Running trainer.

[new] No saved models found. Enter a name of a new model : example example

Model first run.

Choose one or several GPU idxs (separated by comma).

[CPU] : CPU [0] : GeForce GTX 1650 Ti

[0] Which GPU indexes to choose? : 0 0

[0] Autobackup every N hour ( 0..24 ?:help ) : 0 0 [n] Write preview history ( y/n ?:help ) : n [300000] Target iteration : 3000000 3000000 [y] Flip SRC faces randomly ( y/n ?:help ) : y [y] Flip DST faces randomly ( y/n ?:help ) : y [5] Batch_size ( ?:help ) : 8 8 [256] Resolution ( 64-640 ?:help ) : 256 256 [f] Face type ( h/mf/f/wf/head ?:help ) : f f [df] AE architecture ( ?:help ) : df df [256] AutoEncoder dimensions ( 32-1024 ?:help ) : 256 256 [64] Encoder dimensions ( 16-256 ?:help ) : 64 64 [64] Decoder dimensions ( 16-256 ?:help ) : 64 64 [22] Decoder mask dimensions ( 16-256 ?:help ) : 22 22 [n] Eyes and mouth priority ( y/n ?:help ) : n [y] Uniform yaw distribution of samples ( y/n ?:help ) : y [n] Blur out mask ( y/n ?:help ) : n [y] Place models and optimizer on GPU ( y/n ?:help ) : y [y] Use AdaBelief optimizer? ( y/n ?:help ) : y [n] Use learning rate dropout ( n/y/cpu ?:help ) : n n [y] Enable random warp of samples ( y/n ?:help ) : y [0.0] Random hue/saturation/light intensity ( 0.0 .. 0.3 ?:help ) : 0.0 0.0 [0.0] GAN power ( 0.0 .. 5.0 ?:help ) : 0.0 0.0 [0.0] 'True face' power. ( 0.0000 .. 1.0 ?:help ) : 0.0 0.0 [0.0] Face style power ( 0.0..100.0 ?:help ) : 0.0 0.0 [0.0] Background style power ( 0.0..100.0 ?:help ) : 0.0 0.0 [none] Color transfer for src faceset ( none/rct/lct/mkl/idt/sot ?:help ) : none none [y] Enable gradient clipping ( y/n ?:help ) : y [y] Enable pretraining mode ( y/n ?:help ) : y Initializing models: 100%|###############################################################| 5/5 [00:03<00:00, 1.40it/s] Loaded 15843 packed faces from C:\Users\yurch\Downloads\DeepFaceLab_NVIDIA_up_to_RTX2080Ti_internal\pretrain_faces Sort by yaw: 100%|##################################################################| 128/128 [00:00<00:00, 269.41it/s] Sort by yaw: 100%|##################################################################| 128/128 [00:00<00:00, 252.26it/s]

Arsenii101 avatar May 14 '22 12:05 Arsenii101

try change Batch_size to 4

zaiyicheng avatar May 20 '22 23:05 zaiyicheng

try change Batch_size to 4

THIS worked for me !!! Thanks for the tip !

Peter Lunk.

mrlunk avatar Jun 11 '22 10:06 mrlunk

Issue solved / already answered (or it seems like user error), please close it.

joolstorrentecalo avatar Jun 08 '23 22:06 joolstorrentecalo