DeepFaceLab
DeepFaceLab copied to clipboard
iperov
train saehd.bat stuck after pressing key to continue
Running trainer.
[new] No saved models found. Enter a name of a new model : new
Model first run.
Choose one or several GPU idxs (separated by comma).
[CPU] : CPU [0] : NVIDIA GeForce RTX 2070
[0] Which GPU indexes to choose? : 0
[1] Autobackup every N hour ( 0..24 ?:help ) : 1 [n] Write preview history ( y/n ?:help ) : n [0] Target iteration : 0 [y] Flip SRC faces randomly ( y/n ?:help ) : y [y] Flip DST faces randomly ( y/n ?:help ) : y [4] Batch_size ( ?:help ) : 4 [96] Resolution ( 64-640 ?:help ) : 96 [wf] Face type ( h/mf/f/wf/head ?:help ) : wf [df] AE architecture ( ?:help ) : df [256] AutoEncoder dimensions ( 32-1024 ?:help ) : 256 [64] Encoder dimensions ( 16-256 ?:help ) : 64 [64] Decoder dimensions ( 16-256 ?:help ) : 64 [22] Decoder mask dimensions ( 16-256 ?:help ) : 22 [y] Masked training ( y/n ?:help ) : y [n] Eyes and mouth priority ( y/n ?:help ) : n [n] Uniform yaw distribution of samples ( y/n ?:help ) : n [n] Blur out mask ( y/n ?:help ) : n [y] Place models and optimizer on GPU ( y/n ?:help ) : y [n] Use AdaBelief optimizer? ( y/n ?:help ) : n [n] Use learning rate dropout ( n/y/cpu ?:help ) : 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] GAN power ( 0.0 .. 5.0 ?:help ) : 0.0 [0.0] 'True face' power. ( 0.0000 .. 1.0 ?:help ) : 0.0 [0.0] Face style power ( 0.0..100.0 ?:help ) : 0.0 [0.0] Background style power ( 0.0..100.0 ?:help ) : 0.0 [none] Color transfer for src faceset ( none/rct/lct/mkl/idt/sot ?:help ) : none [n] Enable gradient clipping ( y/n ?:help ) : n [n] Enable pretraining mode ( y/n ?:help ) : n Initializing models: 100%|###############################################################| 5/5 [00:01<00:00, 2.71it/s] Loading samples: 100%|############################################################| 2256/2256 [00:04<00:00, 503.05it/s] Loading samples: 100%|##############################################################| 816/816 [00:01<00:00, 461.83it/s] Press any key to continue . . .
gets stuck here
uses the same amount of ram for 8 hours i had it open but never once opened the trainer or got past this stage
using i7 with a rtx 2070 16 gb of ram
I think, but I am not sure, you have to train Quick96 first before do a SHAED training, because the first time I used deepfacelab I did so and it worked, and the second time I used it I didn´t train Quick96 at first and it didn´t work, now I am in the process of training Quick96 in thisone to see if I can train SHAED after
I dont have money so sorry I may quit
On Tue, 15 Feb 2022, 9:25 AM Julia222222, @.***> wrote:
I think, but I am not sure, you have to train Quick96 first before do a SHAED training, because the first time I used deepfacelab I did so and it worked, and the second time I used it I didn´t train Quick96 at first and it didn´t work, now I am in the process of training Quick96 in thisone to see if I can train SHAED after
— Reply to this email directly, view it on GitHub https://github.com/iperov/DeepFaceLab/issues/5473#issuecomment-1039843472, or unsubscribe https://github.com/notifications/unsubscribe-auth/AS6G2HTFQLC4TFSJEMJWR4LU3HIRXANCNFSM5N4HXYTQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you are subscribed to this thread.Message ID: @.***>
I find the solution, you have to use the CPU in the first few interactions and then save and change to GPU
I find the solution, you have to use the CPU in the first few interactions and then save and change to GPU
That method works for quick96 but not for shahd
I think, but I am not sure, you have to train Quick96 first before do a SHAED training, because the first time I used deepfacelab I did so and it worked, and the second time I used it I didn´t train Quick96 at first and it didn´t work, now I am in the process of training Quick96 in thisone to see if I can train SHAED after
maybe this could be the solution
I find the solution, you have to use the CPU in the first few interactions and then save and change to GPU
Using the CPU did start the training, but after saving and then trying to retrain using the GPU, after displaying the current training model status, I got Press any key to continue again and nothing happens.
Using the latest version for windows.
Hello everyone I have also noticed that Saehd does not work with the latest Nvidia drivers. What happens is training Wont open. So I tried gong back to drivers August 2021 and it Works. Do you Guys think They wil fix it ?
Hello everyone I have also noticed that Saehd does not work with the latest Nvidia drivers. What happens is training Wont open. So I tried gong back to drivers August 2021 and it Works. Do you Guys think They wil fix it ?
Thanks a lot 😀😀😀
This works for me properly ~!
The driver version I downgrade to is 471.68 which was released at 20210810.
Hello everyone I have also noticed that Saehd does not work with the latest Nvidia drivers. What happens is training Wont open. So I tried gong back to drivers August 2021 and it Works. Do you Guys think They wil fix it ?
Thanks a lot 😀😀😀
This works for me properly ~!
The driver version I downgrade to is 471.68 which was released at 20210810.
Works with 471.68
Hello everyone I have also noticed that Saehd does not work with the latest Nvidia drivers. What happens is training Wont open. So I tried gong back to drivers August 2021 and it Works. Do you Guys think They wil fix it ?
Thanks a lot 😀😀😀
This works for me properly ~!
The driver version I downgrade to is 471.68 which was released at 20210810.
does this work on a low pc like gtx 1650?
Issue solved / already answered (or it seems like user error), please close it.
