请高人指点下这是什么原因，拜托了！

hongyan888 · 发表于 2022-12-21 02:13:15

星级打分

1
2
3
4
5

平均分:NAN 参与人数:0 我的评分:未评

训练一会就出现该现象，请指点下这是什么原因，拜托了！

  Deepfacelab Me 2022
________ RG 2.55 version was edited by kingboy! ________

Starting. Press "Enter" to stop training and save model.
[00:41:00][#1283232][1168ms][0.3980][0.3246]
E:\DeepfacelabMe2022_Ver2.55_V2\_internal\DeepFaceLabMe\core\imagelib\color_transfer.py:212: RuntimeWarning: invalid value encountered in sqrt
  Qt = eve_t.dot(np.sqrt(np.diag(eva_t))).dot(eve_t.T)
E:\DeepfacelabMe2022_Ver2.55_V2\_internal\python-3.8.5\lib\multiprocessing\process.py:108: RuntimeWarning: invalid value encountered in remainder
  self._target(*self._args, **self._kwargs)
Traceback (most recent call last):
  File "E:\DeepfacelabMe2022_Ver2.55_V2\_internal\DeepFaceLabMe\main.py", line 405, in <module>
arguments.func(arguments)
  File "E:\DeepfacelabMe2022_Ver2.55_V2\_internal\DeepFaceLabMe\main.py", line 162, in process_train
Trainer.main(**kwargs)
  File "mainscripts\Trainer.py", line 699, in mainscripts.Trainer.main
  File "models\ModelBase.py", line 878, in models.ModelBase.ModelBase.get_loss_history_preview
ValueError: cannot convert float NaN to integer
[01:05:32][#1284382][1150ms][nan][nan]
[01:30:45][#1285560][1119ms][nan][nan]
Process Process-22:][1144ms][nan][nan]
Traceback (most recent call last):
  File "E:\DeepfacelabMe2022_Ver2.55_V2\_internal\python-3.8.5\lib\multiprocessing\process.py", line 315, in _bootstrap
self.run()
  File "E:\DeepfacelabMe2022_Ver2.55_V2\_internal\python-3.8.5\lib\multiprocessing\process.py", line 108, in run
self._target(*self._args, **self._kwargs)
  File "models\ModelBase.py", line 919, in models.ModelBase.PreviewHistoryWriter.process
  File "models\ModelBase.py", line 878, in models.ModelBase.ModelBase.get_loss_history_preview
ValueError: cannot convert float NaN to integer
[01:54:41][#1286698][1131ms][nan][nan]