请教大佬：目标头像提取报错。

新手剪辑师

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:NAN  参与人数:0  我的评分:未评

Error while subprocess initialization: Traceback (most recent call last):
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call
    return fn(*args)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InternalError: Dst tensor is not initialized.
         [[{{node _arg_Placeholder_18_0_9}}]]
         [[{{node Assign_1}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\core\joblib\SubprocessorBase.py", line 62, in _subprocess_run
    self.on_initialize(client_dict)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\mainscripts\Extractor.py", line 73, in on_initialize
    self.rects_extractor = facelib.S3FDExtractor(place_model_on_cpu=place_model_on_cpu)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\facelib\S3FDExtractor.py", line 167, in __init__
    self.model.load_weights (model_path)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\core\leras\layers\Saveable.py", line 96, in load_weights
    nn.batch_set_value(tuples)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 29, in batch_set_value
    nn.tf_sess.run(assign_ops, feed_dict=feed_dict)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 929, in run
    run_metadata_ptr)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run
    feed_dict_tensor, options, run_metadata)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run
    run_metadata)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Dst tensor is not initialized.
         [[{{node _arg_Placeholder_18_0_9}}]]
         [[node Assign_1 (defined at H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\core\leras\ops\__init__.py:25) ]]

Traceback (most recent call last):
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\main.py", line 324, in <module>
    arguments.func(arguments)
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\main.py", line 45, in process_extract
    force_gpu_idxs          = [ int(x) for x in arguments.force_gpu_idxs.split(',') ] if arguments.force_gpu_idxs is not None else None,
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\mainscripts\Extractor.py", line 853, in main
    device_config=device_config).run()
  File "H:\视频deep\DeepFaceLab_NVIDIA802_汉化版\_internal\DeepFaceLab\core\joblib\SubprocessorBase.py", line 210, in run
    raise Exception ( "Unable to start subprocesses." )
Exception: Unable to start subprocesses.

以上为报错之后的内容。
之前提取没有问题。
目前按照滚石大佬说的万能丹用法，手动将图片放进了目标照片文件夹，然后进行的提取（就是没有进行视频切割图片那一步）。
之前没有问题。

这个报错目前不知道如何处理，请指教。

fbobby

不懂 帮顶

snyhgzc

升级显卡驱动

kanshu910

没见过，看一看别人的回答。

54724607

不懂帮顶

新手剪辑师

snyhgzc 发表于 2021-10-13 16:11
升级显卡驱动

十分感谢大佬，目前已经解决了问题。
方便的话是否可以帮我指出来，是从哪里看出来是显卡驱动的问题吗？