DFL常见报错答疑搜集贴，不定时更新

faiyoudehe

训练预览界面已经出来了，但是没有开始迭代

517010258

赞一个！

herrfang

来了来了，很有帮助的帖子

iamnickpan

請問使用論壇上的XSeg遮罩後按下Backup出現以下錯誤訊息~有解嗎?
Error: [Errno 2] No such file or directory: 'F:\\DeepFaceLab_NVIDIA_up_to_RTX2080Ti\\workspace\\mode
l\\XSeg_XSeg_256_opt.npy'
Traceback (most recent call last):
  File "F:\DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\mainscripts\Trainer.py", line 19
0, in trainerThread
    model_backup()
  File "F:\DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\mainscripts\Trainer.py", line 73
, in model_backup
    model.create_backup()
  File "F:\DeepFaceLab_NVIDIA_up_to_RTX2080Ti\_internal\DeepFaceLab\models\ModelBase.py", line 437,
in create_backup
    shutil.copy ( str(filename), str(idx_backup_path / Path(filename).name) )
  File "shutil.py", line 245, in copy
  File "shutil.py", line 120, in copyfile
FileNotFoundError: [Errno 2] No such file or directory: 'F:\\DeepFaceLab_NVIDIA_up_to_RTX2080Ti\\wor
kspace\\model\\XSeg_XSeg_256_opt.npy'
Done.
請按任意鍵繼續 . . .

fivezzkk

感谢大佬

yinhelanke

Running trainer.

[new] No saved models found. Enter a name of a new model : 1
1

Model first run.

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

[CPU] : CPU
  [0] : NVIDIA GeForce RTX 3060 Ti

[0] Which GPU indexes to choose? :
0

[24] Autobackup every N hour ( 0..24 ?:help ) :
24
[y] Write preview history ( y/n ?:help ) :
y
[n] Choose image for the preview history ( y/n ) :
n
[0] Target iteration :
0
[n] Flip SRC faces randomly ( y/n ?:help ) :
n
[y] Flip DST faces randomly ( y/n ?:help ) :
y
[8] Batch_size ( ?:help ) :
8
[224] Resolution ( 64-640 ?:help ) :
224
[wf] Face type ( f/wf/head ?:help ) :
wf
[256] AutoEncoder dimensions ( 32-1024 ?:help ) :
256
[1024] Inter dimensions ( 32-2048 ?:help ) :
1024
[64] Encoder dimensions ( 16-256 ?:help ) :
64
[64] Decoder dimensions ( 16-256 ?:help ) :
64
[22] Decoder mask dimensions ( 16-256 ?:help ) :
22
[0.5] Morph factor. ( 0.1 .. 0.5 ?:help ) :
0.5
[n] Uniform yaw distribution of samples ( y/n ?:help ) :
n
[n] Blur out mask ( y/n ?:help ) :
n
[n] Use learning rate dropout ( n/y/cpu ?:help ) :
n
[y] Place models and optimizer on GPU ( y/n ?:help ) :
y
[y] Enable random warp of samples ( y/n ?:help ) :
y
[0.0] GAN power ( 0.0 .. 5.0 ?: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
Initializing models: 100%|###############################################################| 5/5 [00:02<00:00,  1.77it/s]
我的是3060ti卡在这里了，是怎么回事？

chingjqbd

受教了，很有用，谢谢

MC_Li

jokeradmin 发表于 2021-10-26 15:36
反馈一个问题 出现err cp950的话 先检查作业系统是不是繁体的  切换成简体就可以解决(可能极少部分的人才 ...

刚好遇上这 独孤跟猫的神丹都用不到
感谢提供解法

hkhfly

非常感谢分享

dnmsrc

请教一下，源视频转图片的时候，有没有办法让转出来的图片少一点，或者删掉一些不带头像的图片，我这里20分钟的视频转出的图片就有三万张，实在是太慢了。