SAED does not work

[Anonymous]

Training with SEAD does not work.
I did all the steps up to step 6.
The training with xseg also worked, but SAED does not work.
I don’t know what I’m doing wrong. Please help me.

Best regards
aron

Here are my parameters:

Running trainer.

[new] No saved models found. Enter a name of a new model : head20
head20

Model first run.

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

[CPU] : CPU
[0] : NVIDIA GeForce GTX 950M

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

[0] Autobackup every N hour ( 0..24 ?:help ) :
0
[n] Write preview history ( y/n ?:help ) :
n
[0] Target iteration : 10
10
[n] Flip SRC faces randomly ( y/n ?:help ) :
n
[y] Flip DST faces randomly ( y/n ?:help ) :
y
[4] Batch_size ( ?:help ) : 2
2
[128] Resolution ( 64-640 ?:help ) : 64
64
[f] Face type ( h/mf/f/wf/head ?:help ) :
f
[liae-ud] AE architecture ( ?:help ) :
liae-ud
[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
[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
[y] Use AdaBelief optimizer? ( y/n ?:help ) :
y
[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] 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 [00:04<00:00, 1.23it/s]
Loading samples: 100%|###############################################################| 461/461 [00:40<00:00, 11.50it/s]
Loading samples: 100%|###############################################################| 399/399 [00:38<00:00, 10.44it/s]
================== Model Summary ===================
== ==
== Model name: head20_SAEHD ==
== ==
== Current iteration: 0 ==
== ==
==—————- Model Options —————–==
== ==
== resolution: 64 ==
== face_type: f ==
== models_opt_on_gpu: True ==
== archi: liae-ud ==
== ae_dims: 256 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: False ==
== blur_out_mask: False ==
== adabelief: True ==
== lr_dropout: n ==
== random_warp: True ==
== random_hsv_power: 0.0 ==
== true_face_power: 0.0 ==
== face_style_power: 0.0 ==
== bg_style_power: 0.0 ==
== ct_mode: none ==
== clipgrad: False ==
== pretrain: False ==
== autobackup_hour: 0 ==
== write_preview_history: False ==
== target_iter: 10 ==
== random_src_flip: False ==
== random_dst_flip: True ==
== batch_size: 2 ==
== gan_power: 0.0 ==
== gan_patch_size: 8 ==
== gan_dims: 16 ==
== ==
==—————— Running On ——————==
== ==
== Device index: 0 ==
== Name: NVIDIA GeForce GTX 950M ==
== VRAM: 1.35GB ==
== ==
====================================================
Starting. Target iteration: 10. Press “Enter” to stop training and save model.

Trying to do the first iteration. If an error occurs, reduce the model parameters.

!!!
Windows 10 users IMPORTANT notice. You should set this setting in order to work correctly.

View post on imgur.com

!!!
You are training the model from scratch. It is strongly recommended to use a pretrained model to speed up the training and improve the quality.

[deepfakeryKeymaster]

Are you getting an OOM error?
Your card doesn’t have much VRAM so you need to disable some things. Try either or both of these:

[y] Place models and optimizer on GPU ( y/n ?:help ) :
n
[y] Use AdaBelief optimizer? ( y/n ?:help ) :
n

Might also try increasing your page file size.

[Anonymous]

Thanks for your answer.
I implemented the first two suggestions, but still got an error message.
When I try train Quick 96, the error message also appears.
What do you mean with the last point:”Might also try increasing your page file size.”
Can you explain that in a bit more detail?
Best regards
aron

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 GTX 950M

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

[0] Autobackup every N hour ( 0..24 ?:help ) :
0
[n] Write preview history ( y/n ?:help ) :
n
[10] Target iteration :
10
[n] Flip SRC faces randomly ( y/n ?:help ) :
n
[y] Flip DST faces randomly ( y/n ?:help ) :
y
[2] Batch_size ( ?:help ) :
2
[64] Resolution ( 64-640 ?:help ) :
64
[f] Face type ( h/mf/f/wf/head ?:help ) :
f
[liae-ud] AE architecture ( ?:help ) :
liae-ud
[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
[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
[n] Place models and optimizer on GPU ( y/n ?:help ) :
n
[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] 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 [00:02<00:00, 1.72it/s]
Loading samples: 100%|###############################################################| 461/461 [00:41<00:00, 11.06it/s]
Loading samples: 100%|###############################################################| 399/399 [00:38<00:00, 10.41it/s]
Process Process-13:
Traceback (most recent call last):
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleGeneratorFace.py”, line 134, in batch_func
x, = SampleProcessor.process ([sample], self.sample_process_options, self.output_sample_types, self.debug, ct_sample=ct_sample)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleProcessor.py”, line 145, in process
img = get_eyes_mouth_mask()*mask
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleProcessor.py”, line 80, in get_eyes_mouth_mask
return np.clip(mask, 0, 1)
File “<__array_function__ internals>”, line 6, in clip
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\fromnumeric.py”, line 2097, in clip
return _wrapfunc(a, ‘clip’, a_min, a_max, out=out, **kwargs)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\fromnumeric.py”, line 58, in _wrapfunc
return bound(*args, **kwds)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\_methods.py”, line 141, in _clip
um.clip, a, min, max, out=out, casting=casting, **kwargs)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\_methods.py”, line 94, in _clip_dep_invoke_with_casting
return ufunc(*args, out=out, **kwargs)
MemoryError: Unable to allocate 16.0 MiB for an array with shape (2048, 2048, 1) and data type float32

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “multiprocessing\process.py”, line 258, in _bootstrap
File “multiprocessing\process.py”, line 93, in run
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\core\joblib\SubprocessGenerator.py”, line 54, in process_func
gen_data = next (self.generator_func)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleGeneratorFace.py”, line 136, in batch_func
raise Exception (“Exception occured in sample %s. Error: %s” % (sample.filename, traceback.format_exc() ) )
Exception: Exception occured in sample C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\workspace\data_dst\aligned\00081_0.jpg. Error: Traceback (most recent call last):
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleGeneratorFace.py”, line 134, in batch_func
x, = SampleProcessor.process ([sample], self.sample_process_options, self.output_sample_types, self.debug, ct_sample=ct_sample)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleProcessor.py”, line 145, in process
img = get_eyes_mouth_mask()*mask
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\samplelib\SampleProcessor.py”, line 80, in get_eyes_mouth_mask
return np.clip(mask, 0, 1)
File “<__array_function__ internals>”, line 6, in clip
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\fromnumeric.py”, line 2097, in clip
return _wrapfunc(a, ‘clip’, a_min, a_max, out=out, **kwargs)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\fromnumeric.py”, line 58, in _wrapfunc
return bound(*args, **kwds)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\_methods.py”, line 141, in _clip
um.clip, a, min, max, out=out, casting=casting, **kwargs)
File “C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\python-3.6.8\lib\site-packages\numpy\core\_methods.py”, line 94, in _clip_dep_invoke_with_casting
return ufunc(*args, out=out, **kwargs)
MemoryError: Unable to allocate 16.0 MiB for an array with shape (2048, 2048, 1) and data type float32

Drücken Sie eine beliebige Taste . . .

[deepfakeryKeymaster]

Hey Aron,
I just posted a guide which might help. It has some recommendations for DeepFaceLab system optimization.

DeepFaceLab 2.0 Guide

You card doesn’t have much VRAM available which is going to be the major problem, even with really low settings.
Check out this table: https://www.deepfakevfx.com/guides/model-training-settings/
You might need to disable the -U and/or -D model options. Try these settings: LIAE/112/256/64/64/22

Also were you able to run Quick96 at all?

[deepfakeryKeymaster]

I just noticed something else in the path to your DFL:
“C:\Users\aronk\Desktop\11.20. DeepFaceLab_NVIDIA_up_to_RTX2080Ti”
Try having it in your C: directory not the desktop, and remove the space in the folder name

[Anonymous]

Hey deepfakery,

thanks for your reply.
I’ll deal with the guide. I moved DFL to C.
Regarding your question: “Also were you able to run Quick96 at all?” Unfortunately, no.

Best regards
aron

[Author]

Posts