iperov
Help! I am getting this error: Error: No segmented faces found.
Hi All,
I am trying to do some deepfakes for my English assignment, so some help would greatly be appreciated. I am doing a basic, short deepfake, replacing my face with Elon Musk's. I have extracted the faces, and all was going well. When I tried to train it, I got and error message. I have copied the whole console window bellow:
Running trainer.
Model first run. [f] Face type ( h/mf/f/wf/head ?:help ) : wf wf [5] Batch_size ( 2-16 ?:help ) : 2 2 Loaded 0 packed faces from C:\Users[MyUsername]\Documents\DeepFaceLab_NVIDIA\workspace\data_src\aligned Loading samples: 100%|##############################################################| 256/256 [00:00<00:00, 402.45it/s] Filtering: 100%|####################################################################| 256/256 [00:00<00:00, 421.73it/s] Error: No segmented faces found. Traceback (most recent call last): File "C:\Users[MyUsername]\Documents\DeepFaceLab_NVIDIA_internal\DeepFaceLab\mainscripts\Trainer.py", line 57, in trainerThread debug=debug, File "C:\Users[MyUsername]\Documents\DeepFaceLab_NVIDIA_internal\DeepFaceLab\models\Model_XSeg\Model.py", line 17, in init super().init(*args, force_model_class_name='XSeg', **kwargs) File "C:\Users[MyUsername]\Documents\DeepFaceLab_NVIDIA_internal\DeepFaceLab\models\ModelBase.py", line 189, in init self.on_initialize() File "C:\Users[MyUsername]\Documents\DeepFaceLab_NVIDIA_internal\DeepFaceLab\models\Model_XSeg\Model.py", line 133, in on_initialize data_format=nn.data_format) File "C:\Users[MyUsername]\Documents\DeepFaceLab_NVIDIA_internal\DeepFaceLab\samplelib\SampleGeneratorFaceXSeg.py", line 31, in init raise Exception(f"No segmented faces found.") Exception: No segmented faces found.
That was the error message I got. I would greatly appreciated help quickly, because I need to get this done quickly. Also, I set all the settings to there lowest, so that processing power wouldn't be the problem.
Thanks,
xseg is the face masker. read the guide linked on the github
On Wed, Sep 2, 2020 at 3:45 PM HackerBoy [email protected] wrote:
this is xseg.
Okay, so what can I do to fix the problem?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/iperov/DeepFaceLab/issues/881#issuecomment-685957620, or unsubscribe https://github.com/notifications/unsubscribe-auth/APLSDRHJOFPQP5HQNDN4PYDSD2OGBANCNFSM4QSZP7LQ .
Dont train with xseg if you didn't use it prior. Use quick96, sounds like you used that. Came across this myself. test1230-lab pointed me to resolve it.
I'm facing the same problem. I mask a few faces, train with XSeg and results are pretty good. Then I apply the masks, to both src and dst. In the XSeg viewer there is a mask on all faces. However, when I'm merging, around 40 % of the frames "do not have a face". In my merged_mask folder there are only a few faces, and a small percentage of them have the mask applied.
clues?
I'm facing the same problem. I mask a few faces, train with XSeg and results are pretty good. Then I apply the masks, to both src and dst. In the XSeg viewer there is a mask on all faces. However, when I'm merging, around 40 % of the frames "do not have a face". In my merged_mask folder there are only a few faces, and a small percentage of them have the mask applied.
clues?
Did you get any clues on this? I'm having the same results, random missing faces....
"No segmented faces found." What this means is that there are literally no segments. You will Launch the XSeg editor to create one or more segments.
- XSeg) data_dst mask - edit.bat
- XSeg) data_src mask - edit.bat
Issue solved / already answered (or it seems like user error), please close it.
