deepfacelab中文论坛

 找回密码
 立即注册
查看: 139|回复: 3

小白求教大佬!进入训练模块后提示,然后就没然后了

[复制链接]

1

主题

2

帖子

20

积分

初级丹童

Rank: 1

积分
20
 楼主| 发表于 2022-11-25 14:31:00 | 显示全部楼层 |阅读模式
星级打分
  • 1
  • 2
  • 3
  • 4
  • 5
平均分:NAN  参与人数:0  我的评分:未评
File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\mainscripts\Trainer.py", line 110, in trainerThread
    reduce_clutter= kwargs.get('reduce_clutter', False)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\models\ModelBase.py", line 265, in __init__
    self.on_initialize()
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\models\Model_AMP\Model.py", line 445, in on_initialize
    self.G_weights = self.encoder.get_weights() self.decoder.get_weights()
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 77, in get_weights
    self.build()
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 65, in build
    self._build_sub(v[name],name)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 35, in _build_sub
    layer.build()
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 65, in build
    self._build_sub(v[name],name)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 33, in _build_sub
    layer.build_weights()
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\DeepFaceLab\core\leras\layers\Conv2D.py", line 61, in build_weights
    self.weight = tf.get_variable("weight", (self.kernel_size,self.kernel_size,self.in_ch,self.out_ch), dtype=self.dtype, initializer=kernel_initializer, trainable=self.trainable )
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1595, in get_variable
    aggregation=aggregation)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1338, in get_variable
    aggregation=aggregation)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 593, in get_variable
    aggregation=aggregation)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 545, in _true_getter
    aggregation=aggregation)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 963, in _get_single_variable
    aggregation=aggregation)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 266, in __call__
    return cls._variable_v1_call(*args, **kwargs)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 227, in _variable_v1_call
    shape=shape)
  File "D:\BaiduNetdiskDownload\RTX3000-4090_2022_10_14\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 205, in <lambda>
    previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)

回复

使用道具 举报

4

主题

32

帖子

331

积分

初级丹师

Rank: 3Rank: 3

积分
331
发表于 2022-11-25 16:39:39 | 显示全部楼层
虚拟内存搞大点试试
回复 支持 反对

使用道具 举报

1

主题

6

帖子

165

积分

高级丹童

Rank: 2

积分
165
发表于 2022-11-25 17:47:30 | 显示全部楼层
我也是同样问题 ,启动训练中,然后出现一堆英文,然后就没有然后了,我i虚拟内存都已经64G了 这是什么鬼!!!!
回复 支持 反对

使用道具 举报

2

主题

35

帖子

228

积分

初级丹师

Rank: 3Rank: 3

积分
228
发表于 2022-11-27 01:45:46 | 显示全部楼层
学习一下
回复

使用道具 举报

QQ|Archiver|手机版|小黑屋|deepfacelab中文论坛 |网站地图

GMT+8, 2022-12-9 08:24 , Processed in 0.075417 second(s), 34 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

快速回复 返回顶部 返回列表