I get this errors and i do not know what to do

[Anonymous]

Running trainer.

Loading XSeg model…

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

[CPU] : CPU
[0] : NVIDIA GeForce RTX 2080 Super
[1] : Intel(R) UHD Graphics 630

[1] Which GPU indexes to choose? : 1
1

Press enter in 2 seconds to override model settings.
[n] Restart training? ( y/n ?:help ) :
n
[8] Batch_size ( 2-16 ?:help ) :
8
[n] Enable pretraining mode ( y/n ) :
n
Loading samples: 100%|########################################################| 146146/146146 [06:15<00:00, 389.70it/s]
Loaded 63012 packed faces from C:\Users\sunni\OneDrive\Desktop\paul chang New\workspace\data_dst\aligned
Filtering: 100%|#############################################################| 209158/209158 [02:43<00:00, 1282.43it/s]
Using 288 segmented samples.
================= Model Summary ==================
== ==
== Model name: XSeg ==
== ==
== Current iteration: 4519 ==
== ==
==————— Model Options —————-==
== ==
== face_type: wf ==
== pretrain: False ==
== batch_size: 8 ==
== ==
==—————– Running On —————–==
== ==
== Device index: 1 ==
== Name: Intel(R) UHD Graphics 630 ==
== VRAM: 29.57GB ==
== ==
==================================================
Starting. Press “Enter” to stop training and save model.
Traceback (most recent call last):
File “C:\Users\sunni\OneDrive\Desktop\paul chang New\_internal\DeepFaceLab\main.py”, line 343, in <module>
arguments.func(arguments)
File “C:\Users\sunni\OneDrive\Desktop\paul chang New\_internal\DeepFaceLab\main.py”, line 132, in process_train
Trainer.main(**kwargs)
File “C:\Users\sunni\OneDrive\Desktop\paul chang New\_internal\DeepFaceLab\mainscripts\Trainer.py”, line 317, in main
lh_img = models.ModelBase.get_loss_history_preview(loss_history_to_show, iter, w, c)
File “C:\Users\sunni\OneDrive\Desktop\paul chang New\_internal\DeepFaceLab\models\ModelBase.py”, line 627, in get_loss_history_preview
ph_max = int ( (plist_max[col][p] / plist_abs_max) * (lh_height-1) )
ValueError: cannot convert float NaN to integer
[

[deepfakeryKeymaster]

I would move everything from the OneDrive folder to Documents or C:, and also use folders with no spaces in the name.

[genesis1Participant]

I’m getting a weird thing when I use Xseg data_src trained mask apply. The apps on my desktop start blinking with a green tick. I looked it up and it says a green tick on the shortcuts on the desktop mean its been backed up to one drive. I’m not even using ms one drive. And I disconnected from the Internet when using dfl so nothing is being backed up.

[defalafaParticipant]

just hit “F5” it goes away

[yeonslParticipant]

its error
reinstall deepfacelab and old workplace folder move to new install workplace folder
its gonna work ~

[myaiassetParticipant]

were you able to resolve this? I’m having the same problem

[kvartalaParticipant]

It looks like the issue happened because GPU 1 was selected, which is your Intel UHD Graphics 630, not the RTX 2080 Super. For DeepFaceLab, you should usually pick GPU 0, since that’s the NVIDIA card and the one actually meant for training.

The error at the end, ValueError: cannot convert float NaN to integer, usually means the loss history broke after startup, often because the training device was wrong or the run produced invalid Grabovoi numbers/values right away.

Try this:

restart the trainer
choose 0 for GPU index, not 1
keep batch size at 8 only if your RTX can handle it, otherwise lower it to 4
start training again

If it still crashes even on GPU 0, then the model files or loss history may already be corrupted, and you may need to clear the preview/history files or restart the XSeg model training.

So the main problem here is: you picked the Intel integrated graphics instead of the RTX.

[Author]

Posts