DFL常见报错答疑搜集贴，不定时更新

dfldataer

aaa2002911 发表于 2021-6-26 00:34
再分解一次视频试试。不确定。用jpg试试

解决了，新装的系统是GHOST的，单独装下CUDA 11升级驱动即可

kensou2003

学习了，感谢分享

aaa2002911

dfldataer 发表于 2021-6-26 17:54
解决了，新装的系统是GHOST的，单独装下CUDA 11升级驱动即可

所以说，你还是有点一段错误代码没有复制
在论坛很多东西不方便回答就是没有全部代码

dfldataer

不看错误代码也行，先把环境重装一遍可以解决80%问题，哈哈哈

dreamtear

请问这样之后就没反应了怎么办

00cat

模型 : 192 HD-UD_SAEHD

DFL 版本 : RTX3000_build_06_02_2021

訓練模型存檔後就跳出這段 求大佬指點


Starting. Press "Enter" to stop training and save model.
Error: 'cp950' codec can't encode character '\u8d39' in position 1904: illegal multibyte sequence
Traceback (most recent call last):
  File "F:\DeepFaceLab\DFL_RTX3000_build_06_02_2021\_internal\DeepFaceLab\mainscripts\Trainer.py", line 178, in trainerThread
    model_save()
  File "F:\DeepFaceLab\DFL_RTX3000_build_06_02_2021\_internal\DeepFaceLab\mainscripts\Trainer.py", line 77, in model_save
    model.save()
  File "F:\DeepFaceLab\DFL_RTX3000_build_06_02_2021\_internal\DeepFaceLab\models\ModelBase.py", line 389, in save
    Path( self.get_summary_path() ).write_text( self.get_summary_text() )
  File "pathlib.py", line 1216, in write_text
UnicodeEncodeError: 'cp950' codec can't encode character '\u8d39' in position 1904: illegal multibyte sequence
Done.
請按任意鍵繼續 . . .

charry

好贴回复

lzhmhznr

强烈支持

zaxpf123

谢谢大佬

可乐好久才

在训练模型的时候，出现这个问题，请教大佬怎么解决，我的显卡是rtx 3050
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

启动训练程序.

[new] 没有发现模型，输入一个名字新建模型 : test
test

首次运行模型。

可用设备列表：

[CPU] : CPU
  [0] : GeForce RTX 3050 Laptop GPU

[0] 选择哪一个设备？ : 0
0

Initializing models: 100%|###############################################################| 5/5 [00:02<00:00,  1.72it/s]
实例加载中: 100%|###################################################################| 293/293 [00:00<00:00, 458.08it/s]
实例加载中: 100%|###################################################################| 836/836 [00:01<00:00, 489.60it/s]
================== Model Summary ===================
==                                                ==
==        Model name: test_Quick96                ==
==                                                ==
== Current iteration: 0                           ==
==                                                ==
==---------------- Model Options -----------------==
==                                                ==
==        batch_size: 4                           ==
==                                                ==
==------------------ Running On ------------------==
==                                                ==
==      Device index: 0                           ==
==              Name: GeForce RTX 3050 Laptop GPU ==
==              VRAM: 4.00GB                      ==
==                                                ==
====================================================

Deepfake中文网：www.deepfaker.xyz
公众号：托尼是塔克
=============================================

启动中. 按 "Enter" 停止训练并保存进度。

保存时间|迭代次数|单次时间|源损失|目标损失

正在尝试运行第一个迭代. 如果出现错误, 请降低参数配置

!!!
rtx3000系列请注意. 为了正常运行程序你需开始硬件加速GPU计划
https://www.deepfaker.xyz/?p=2171
!!!
Error: OOM when allocating tensor of shape [128,1152] and type float
         [[node src_dst_opt_1/ones_10 (defined at F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\ops\__init__.py:207) ]]

Original stack trace for 'src_dst_opt_1/ones_10':
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\ModelBase.py", line 189, in __init__
    self.on_initialize()
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\Model_Quick96\Model.py", line 77, in on_initialize
    self.src_dst_opt.initialize_variables(self.src_dst_trainable_weights, vars_on_cpu=optimizer_vars_on_cpu )
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\optimizers\RMSprop.py", line 41, in initialize_variables
    lr_rnds = [ nn.random_binomial( v.shape, p=self.lr_dropout, dtype=v.dtype) for v in trainable_weights ]
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\optimizers\RMSprop.py", line 41, in <listcomp>
    lr_rnds = [ nn.random_binomial( v.shape, p=self.lr_dropout, dtype=v.dtype) for v in trainable_weights ]
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 207, in random_binomial
    array_ops.ones(shape, dtype=dtype), array_ops.zeros(shape, dtype=dtype))
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 201, in wrapper
    return target(*args, **kwargs)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\array_ops.py", line 3132, in ones
    output = fill(shape, constant(one, dtype=dtype), name=name)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 201, in wrapper
    return target(*args, **kwargs)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\array_ops.py", line 239, in fill
    result = gen_array_ops.fill(dims, value, name=name)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 3357, in fill
    "Fill", dims=dims, value=value, name=name)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 750, in _apply_op_helper
    attrs=attr_protos, op_def=op_def)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3536, in _create_op_internal
    op_def=op_def)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 1990, in __init__
    self._traceback = tf_stack.extract_stack()

Traceback (most recent call last):
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1375, in _do_call
    return fn(*args)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1360, in _run_fn
    target_list, run_metadata)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1453, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor of shape [128,1152] and type float
         [[{{node src_dst_opt_1/ones_10}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\mainscripts\Trainer.py", line 130, in trainerThread
    iter, iter_time = model.train_one_iter()
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\ModelBase.py", line 462, in train_one_iter
    losses = self.onTrainOneIter()
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\Model_Quick96\Model.py", line 276, in onTrainOneIter
    warped_dst, target_dst, target_dstm)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\Model_Quick96\Model.py", line 178, in src_dst_train
    self.target_dstm:target_dstm,
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 968, in run
    run_metadata_ptr)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1191, in _run
    feed_dict_tensor, options, run_metadata)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1369, in _do_run
    run_metadata)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1394, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor of shape [128,1152] and type float
         [[node src_dst_opt_1/ones_10 (defined at F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\ops\__init__.py:207) ]]

Original stack trace for 'src_dst_opt_1/ones_10':
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\ModelBase.py", line 189, in __init__
    self.on_initialize()
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\models\Model_Quick96\Model.py", line 77, in on_initialize
    self.src_dst_opt.initialize_variables(self.src_dst_trainable_weights, vars_on_cpu=optimizer_vars_on_cpu )
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\optimizers\RMSprop.py", line 41, in initialize_variables
    lr_rnds = [ nn.random_binomial( v.shape, p=self.lr_dropout, dtype=v.dtype) for v in trainable_weights ]
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\optimizers\RMSprop.py", line 41, in <listcomp>
    lr_rnds = [ nn.random_binomial( v.shape, p=self.lr_dropout, dtype=v.dtype) for v in trainable_weights ]
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 207, in random_binomial
    array_ops.ones(shape, dtype=dtype), array_ops.zeros(shape, dtype=dtype))
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 201, in wrapper
    return target(*args, **kwargs)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\array_ops.py", line 3132, in ones
    output = fill(shape, constant(one, dtype=dtype), name=name)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 201, in wrapper
    return target(*args, **kwargs)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\array_ops.py", line 239, in fill
    result = gen_array_ops.fill(dims, value, name=name)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 3357, in fill
    "Fill", dims=dims, value=value, name=name)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 750, in _apply_op_helper
    attrs=attr_protos, op_def=op_def)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3536, in _create_op_internal
    op_def=op_def)
  File "F:\Program Files (x86)\DeepFaceLab_NVIDIA20210104\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 1990, in __init__
    self._traceback = tf_stack.extract_stack()