新人求帮忙，不知道是电脑硬件不行还是设置问题，代码.....

tjj

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:NAN  参与人数:0  我的评分:未评

bs已调到2，请问是我硬件不行还是设置问题，请帮忙
两秒内按下Enter键可以重新设置模型参数.
[0] 几个小时备份一次 ( 0..24 英文输入法下按?获取帮助 ) :
0
[n] 保存预览历史记录 ( y/n 英文输入法下按?获取帮助 ) :
n
[0] 目标迭代次数 :
0
[y] 人脸随机翻转 ( y/n 英文输入法下按?获取帮助 ) :
y
[8] 批量大小 ( 英文输入法下按?获取帮助 ) : 2
2
[y] Masked training ( y/n 英文输入法下按?获取帮助 ) :
y
[n] 眼睛和嘴巴优先 Eyes and mouth priority ( y/n 英文输入法下按?获取帮助 ) :
n
[y] 侧脸优化 Uniform yaw distribution of samples ( y/n 英文输入法下按?获取帮助 )
:
y
[y] 把模型和优化器放在GPU上 ( y/n 英文输入法下按?获取帮助 ) :
y
[y] 使用 AdaBelief 优化器? ( y/n 英文输入法下按?获取帮助 ) :
y
[n] 学习率下降 ( n/y/cpu 英文输入法下按?获取帮助 ) :
n
[y] 随机扭曲 ( y/n 英文输入法下按?获取帮助 ) :
y
[0.0] GAN强度 ( 0.0 .. 1.0 英文输入法下按?获取帮助 ) :
0.0
[0.0] '真脸强度. ( 0.0000 .. 1.0 英文输入法下按?获取帮助 ) :
0.0
[0.0] 人脸风格强度 ( 0.0..100.0 英文输入法下按?获取帮助 ) :
0.0
[0.0] 背景风格强度 ( 0.0..100.0 英文输入法下按?获取帮助 ) :
0.0
[none] 颜色转换模式 ( none/rct/lct/mkl/idt/sot 英文输入法下按?获取帮助 ) :
none
[n] 启用梯度剪裁 ( y/n 英文输入法下按?获取帮助 ) :
n
[y] 启用预训练 ( y/n 英文输入法下按?获取帮助 ) : n
Initializing models:  80%|#################6    | 4/5 [12:13<03:03, 183.28s/it]
Error: OOM when allocating tensor of shape [3,3,256,1024] and type float
         [[node src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const (
defined at D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab
\core\leras\optimizers\AdaBelief.py:37) ]]

Caused by op 'src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const', d
efined at:
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\ma
inscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\mo
dels\ModelBase.py", line 200, in __init__
    self.on_initialize()
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\mo
dels\Model_SAEHD\Model.py", line 323, in on_initialize
    self.src_dst_opt.initialize_variables (self.src_dst_trainable_weights, vars_
on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu
')
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\co
re\leras\optimizers\AdaBelief.py", line 37, in initialize_variables
    vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape,
dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v
in trainable_weights }
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\co
re\leras\optimizers\AdaBelief.py", line 37, in <dictcomp>
    vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape,
dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v
in trainable_weights }
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 1479, in get_var
iable
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 1220, in get_var
iable
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 547, in get_vari
able
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 499, in _true_ge
tter
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 911, in _get_sin
gle_variable
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 213, in __call__
    return cls._variable_v1_call(*args, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 176, in _variable_v1_
call
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 155, in <lambda>
    previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 2495, in default
_variable_creator
    expected_shape=expected_shape, import_scope=import_scope)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 217, in __call__
    return super(VariableMetaclass, cls).__call__(*args, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 1395, in __init__
    constraint=constraint)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 1503, in _init_from_a
rgs
    initial_value(), name="initial_value", dtype=dtype)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 883, in <lambda>

    shape.as_list(), dtype=dtype, partition_info=partition_info)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\init_ops.py", line 230, in __call__
    self.value, dtype=dtype, shape=shape, verify_shape=verify_shape)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\constant_op.py", line 179, in const
ant_v1
    allow_broadcast=False)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\constant_op.py", line 289, in _cons
tant_impl
    name=name).outputs[0]
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op
    op_def=op_def)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\ops.py", line 1801, in __init__
    self._traceback = tf_stack.extract_stack()

ResourceExhaustedError (see above for traceback): OOM when allocating tensor of
shape [3,3,256,1024] and type float
         [[node src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const (
defined at D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab
\core\leras\optimizers\AdaBelief.py:37) ]]

Traceback (most recent call last):
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call
    return fn(*args)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_se
ssionrun
    run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocat
ing tensor of shape [3,3,256,1024] and type float
         [[{{node src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const
}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\ma
inscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\mo
dels\ModelBase.py", line 200, in __init__
    self.on_initialize()
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\mo
dels\Model_SAEHD\Model.py", line 619, in on_initialize
    model.init_weights()
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\co
re\leras\layers\Saveable.py", line 104, in init_weights
    nn.init_weights(self.get_weights())
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\co
re\leras\ops\__init__.py", line 48, in init_weights
    nn.tf_sess.run (ops)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 929, in run
    run_metadata_ptr)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 1152, in _run
    feed_dict_tensor, options, run_metadata)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run
    run_metadata)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocat
ing tensor of shape [3,3,256,1024] and type float
         [[node src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const (
defined at D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab
\core\leras\optimizers\AdaBelief.py:37) ]]

Caused by op 'src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const', d
efined at:
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\ma
inscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\mo
dels\ModelBase.py", line 200, in __init__
    self.on_initialize()
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\mo
dels\Model_SAEHD\Model.py", line 323, in on_initialize
    self.src_dst_opt.initialize_variables (self.src_dst_trainable_weights, vars_
on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu
')
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\co
re\leras\optimizers\AdaBelief.py", line 37, in initialize_variables
    vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape,
dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v
in trainable_weights }
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab\co
re\leras\optimizers\AdaBelief.py", line 37, in <dictcomp>
    vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape,
dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v
in trainable_weights }
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 1479, in get_var
iable
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 1220, in get_var
iable
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 547, in get_vari
able
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 499, in _true_ge
tter
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 911, in _get_sin
gle_variable
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 213, in __call__
    return cls._variable_v1_call(*args, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 176, in _variable_v1_
call
    aggregation=aggregation)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 155, in <lambda>
    previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 2495, in default
_variable_creator
    expected_shape=expected_shape, import_scope=import_scope)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 217, in __call__
    return super(VariableMetaclass, cls).__call__(*args, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 1395, in __init__
    constraint=constraint)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variables.py", line 1503, in _init_from_a
rgs
    initial_value(), name="initial_value", dtype=dtype)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\variable_scope.py", line 883, in <lambda>

    shape.as_list(), dtype=dtype, partition_info=partition_info)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\ops\init_ops.py", line 230, in __call__
    self.value, dtype=dtype, shape=shape, verify_shape=verify_shape)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\constant_op.py", line 179, in const
ant_v1
    allow_broadcast=False)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\constant_op.py", line 289, in _cons
tant_impl
    name=name).outputs[0]
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op
    op_def=op_def)
  File "D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\python-3.6.8\l
ib\site-packages\tensorflow\python\framework\ops.py", line 1801, in __init__
    self._traceback = tf_stack.extract_stack()

ResourceExhaustedError (see above for traceback): OOM when allocating tensor of
shape [3,3,256,1024] and type float
         [[node src_dst_opt/vs_inter/upscale1/conv1/weight_0/Initializer/Const (
defined at D:\deepfakes\DeepFaceLab_0104汉化版-10.20系显卡\_internal\DeepFaceLab
\core\leras\optimizers\AdaBelief.py:37) ]]

xiaoxin

显卡不行，换个老版本的试试。

gamecp9

不懂帮顶

wanghao

这个版本已经完全抛弃小显存了。没6g玩不起

1234qwer111

路过学习

tjj

wanghao 发表于 2021-4-21 09:02
这个版本已经完全抛弃小显存了。没6g玩不起

谢谢大佬~

tjj

xiaoxin 发表于 2021-4-21 07:49
显卡不行，换个老版本的试试。

谢谢，那我换个1660的显卡行不行

3dw4rd

旧版本显示，显卡8gb，新版本显示6.58gb，有哪个大大知道什么原因吗?会不会有影响?用回旧版会比较好吗?

tjj

路过支持一下