新人求助：训练SAEHD模型出现问题

一位优秀的人

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:NAN  参与人数:0  我的评分:未评

求大佬们看一下有什么问题


Running trainer.

Choose one of saved models, or enter a name to create a new model.
[r] : rename
[d] : delete

[0] : WF 320 DF-UD - latest
:
0
Loading WF 320 DF-UD_SAEHD model...

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

[CPU] : CPU
  [0] : NVIDIA GeForce RTX 3060 Laptop GPU

[0] Which GPU indexes to choose? :
0

Initializing models: 100%|###############################################################| 5/5 [00:02<00:00,  1.82it/s]
Loaded 15843 packed faces from C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\pretrain_faces
Sort by yaw: 100%|##################################################################| 128/128 [00:00<00:00, 404.98it/s]
Sort by yaw: 100%|##################################################################| 128/128 [00:00<00:00, 402.71it/s]
======================== Model Summary ========================
==                                                           ==
==            Model name: WF 320 DF-UD_SAEHD                 ==
==                                                           ==
==     Current iteration: 1001991                            ==
==                                                           ==
==---------------------- Model Options ----------------------==
==                                                           ==
==            resolution: 320                                ==
==             face_type: wf                                 ==
==     models_opt_on_gpu: True                               ==
==                 archi: df-ud                              ==
==               ae_dims: 256                                ==
==                e_dims: 64                                 ==
==                d_dims: 64                                 ==
==           d_mask_dims: 22                                 ==
==       masked_training: True                               ==
==           uniform_yaw: True                               ==
==            lr_dropout: n                                  ==
==           random_warp: False                              ==
==             gan_power: 0.0                                ==
==       true_face_power: 0.0                                ==
==      face_style_power: 0.0                                ==
==        bg_style_power: 0.0                                ==
==               ct_mode: none                               ==
==              clipgrad: False                              ==
==              pretrain: True                               ==
==       autobackup_hour: 0                                  ==
== write_preview_history: False                              ==
==           target_iter: 0                                  ==
==           random_flip: True                               ==
==            batch_size: 8                                  ==
==       eyes_mouth_prio: False                              ==
==         blur_out_mask: False                              ==
==             adabelief: True                               ==
==      random_hsv_power: 0.0                                ==
==        gan_patch_size: 40                                 ==
==              gan_dims: 16                                 ==
==                                                           ==
==----------------------- Running On ------------------------==
==                                                           ==
==          Device index: 0                                  ==
==                  Name: NVIDIA GeForce RTX 3060 Laptop GPU ==
==                  VRAM: 3.41GB                             ==
==                                                           ==
===============================================================
Starting. Press "Enter" to stop training and save model.
Error: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[2048,256,3,3] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node Conv2D_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:101) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_5/concat/_465]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: OOM when allocating tensor with shape[2048,256,3,3] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node Conv2D_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:101) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

Errors may have originated from an input operation.
Input Source operations connected to node Conv2D_28:
Pad_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:87)
decoder_dst/upscale0/conv1/weight/read (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:61)

Input Source operations connected to node Conv2D_28:
Pad_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:87)
decoder_dst/upscale0/conv1/weight/read (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:61)

Original stack trace for 'Conv2D_28':
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\ModelBase.py", line 193, in __init__
    self.on_initialize()
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 410, in on_initialize
    gpu_pred_dst_dst, gpu_pred_dst_dstm = self.decoder_dst(gpu_dst_code)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 117, in __call__
    return self.forward(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py", line 221, in forward
    x = self.upscale0(z)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 117, in __call__
    return self.forward(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py", line 71, in forward
    x = self.conv1(x)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\LayerBase.py", line 14, in __call__
    return self.forward(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py", line 101, in forward
    x = tf.nn.conv2d(x, weight, strides, 'VALID', dilations=dilations, data_format=nn.data_format)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 206, in wrapper
    return target(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 2397, in conv2d
    name=name)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 972, in conv2d
    data_format=data_format, dilations=dilations, name=name)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_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 "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3569, in _create_op_internal
    op_def=op_def)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 2045, in __init__
    self._traceback = tf_stack.extract_stack_for_node(self._c_op)

Traceback (most recent call last):
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1375, in _do_call
    return fn(*args)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1360, in _run_fn
    target_list, run_metadata)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_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: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[2048,256,3,3] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[{{node Conv2D_28}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_5/concat/_465]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: OOM when allocating tensor with shape[2048,256,3,3] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[{{node Conv2D_28}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\mainscripts\Trainer.py", line 129, in trainerThread
    iter, iter_time = model.train_one_iter()
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\ModelBase.py", line 474, in train_one_iter
    losses = self.onTrainOneIter()
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 774, in onTrainOneIter
    src_loss, dst_loss = self.src_dst_train (warped_src, target_src, target_srcm, target_srcm_em, warped_dst, target_dst, target_dstm, target_dstm_em)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 584, in src_dst_train
    self.target_dstm_em:target_dstm_em,
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 968, in run
    run_metadata_ptr)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1191, in _run
    feed_dict_tensor, options, run_metadata)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1369, in _do_run
    run_metadata)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_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)  # pylint: disable=no-value-for-parameter
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[2048,256,3,3] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node Conv2D_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:101) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_5/concat/_465]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: OOM when allocating tensor with shape[2048,256,3,3] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node Conv2D_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:101) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

Errors may have originated from an input operation.
Input Source operations connected to node Conv2D_28:
Pad_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:87)
decoder_dst/upscale0/conv1/weight/read (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:61)

Input Source operations connected to node Conv2D_28:
Pad_28 (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:87)
decoder_dst/upscale0/conv1/weight/read (defined at C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:61)

Original stack trace for 'Conv2D_28':
  File "threading.py", line 884, in _bootstrap
  File "threading.py", line 916, in _bootstrap_inner
  File "threading.py", line 864, in run
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\ModelBase.py", line 193, in __init__
    self.on_initialize()
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 410, in on_initialize
    gpu_pred_dst_dst, gpu_pred_dst_dstm = self.decoder_dst(gpu_dst_code)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 117, in __call__
    return self.forward(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py", line 221, in forward
    x = self.upscale0(z)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 117, in __call__
    return self.forward(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py", line 71, in forward
    x = self.conv1(x)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\LayerBase.py", line 14, in __call__
    return self.forward(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Conv2D.py", line 101, in forward
    x = tf.nn.conv2d(x, weight, strides, 'VALID', dilations=dilations, data_format=nn.data_format)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 206, in wrapper
    return target(*args, **kwargs)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 2397, in conv2d
    name=name)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 972, in conv2d
    data_format=data_format, dilations=dilations, name=name)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_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 "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3569, in _create_op_internal
    op_def=op_def)
  File "C:\Users\80426\Downloads\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 2045, in __init__
    self._traceback = tf_stack.extract_stack_for_node(self._c_op)

wtxx8888

OOM问百遍了，爆显存的提示。减低batch_size吧。
320的丹，你3.4G的显存还想BS8？BS4都不一定能跑

一位优秀的人

wtxx8888 发表于 2022-7-8 19:40
OOM问百遍了，爆显存的提示。减低batch_size吧。
320的丹，你3.4G的显存还想BS8？BS4都不一定能跑

请问怎么降低batch_size呢

maou

去论坛教程区过一遍再说吧，那里有你想知道的答案

15554785588

wtxx8888 发表于 2022-7-8 19:40
OOM问百遍了，爆显存的提示。减低batch_size吧。
320的丹，你3.4G的显存还想BS8？BS4都不一定能跑

我估计跑2都困难

15554785588

一位优秀的人 发表于 2022-7-8 20:08
请问怎么降低batch_size呢

执行saehd之后，cmd窗口让你选择GPU之后会出现“2秒内按下enter更改参数”，在那里面一项项的改

一位优秀的人

15554785588 发表于 2022-7-8 21:19
执行saehd之后，cmd窗口让你选择GPU之后会出现“2秒内按下enter更改参数”，在那里面一项项的改 ...

谢谢大佬

15554785588

一位优秀的人 发表于 2022-7-8 21:49
谢谢大佬

太客气了，我不是大佬，我也是个小学生

qq631250213

学习了··············