运行到第六步训练总是报错

99年战争指挥官

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:NAN  参与人数:0  我的评分:未评

请问这是什么情况啊，运行到第六步训练的时候，总是报错，应该怎么解决啊，各位老哥

suhgnksg

你模型文件完整么？

whl716694

别用中文版的

poiu88

别用中文版

1234qwer111

不懂帮顶

99年战争指挥官

suhgnksg 发表于 2021-7-15 17:24
你模型文件完整么？

应该是完整的啊，用里面给的托尼也试了一下，也是报错这个

99年战争指挥官

whl716694 发表于 2021-7-15 17:42
别用中文版的

用英文的也是一样，都是报同样的错误

Initializing models:  60%|#####################################8                         | 3/5 [00:10<00:07,  3.54s/it]

Error while processing data: Traceback (most recent call last):
  File "G:\facelab\_internal\DeepFaceLab\core\joblib\SubprocessorBase.py", line 71, in _subprocess_run
    result = self.process_data(data)
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\CA.py", line 48, in process_data
    weights = CAInitializerSubprocessor.generate (shape, dtype)
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\CA.py", line 29, in generate
    x = x + np.transpose(x, (0,1,3,2) ) * (1-np.eye(basis_size))
MemoryError: Unable to allocate 96.2 MiB for an array with shape (2048, 171, 6, 6) and data type float64

Initializing models:  60%|#####################################8                         | 3/5 [00:12<00:08,  4.23s/it]
Error: list indices must be integers or slices, not tuple
Traceback (most recent call last):
  File "G:\facelab\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "G:\facelab\_internal\DeepFaceLab\models\ModelBase.py", line 200, in __init__
    self.on_initialize()
  File "G:\facelab\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 619, in on_initialize
    model.init_weights()
  File "G:\facelab\_internal\DeepFaceLab\core\leras\layers\Saveable.py", line 104, in init_weights
    nn.init_weights(self.get_weights())
  File "G:\facelab\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 51, in init_weights
    nn.batch_set_value( [*zip(ca_tuples_w, nn.initializers.ca.generate_batch (ca_tuples))] )
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\__init__.py", line 18, in generate_batch
    return CAInitializerSubprocessor (data_list).run()
  File "G:\facelab\_internal\DeepFaceLab\core\joblib\SubprocessorBase.py", line 257, in run
    data = self.get_data(cli.host_dict)
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\CA.py", line 67, in get_data
    shape, dtype = self.data_list[idx]
TypeError: list indices must be integers or slices, not tuple

99年战争指挥官

poiu88 发表于 2021-7-15 18:05
别用中文版

用英文也是一样，都是报同样的错误
Initializing models:  60%|#####################################8                         | 3/5 [00:10<00:07,  3.54s/it]

Error while processing data: Traceback (most recent call last):
  File "G:\facelab\_internal\DeepFaceLab\core\joblib\SubprocessorBase.py", line 71, in _subprocess_run
    result = self.process_data(data)
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\CA.py", line 48, in process_data
    weights = CAInitializerSubprocessor.generate (shape, dtype)
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\CA.py", line 29, in generate
    x = x + np.transpose(x, (0,1,3,2) ) * (1-np.eye(basis_size))
MemoryError: Unable to allocate 96.2 MiB for an array with shape (2048, 171, 6, 6) and data type float64

Initializing models:  60%|#####################################8                         | 3/5 [00:12<00:08,  4.23s/it]
Error: list indices must be integers or slices, not tuple
Traceback (most recent call last):
  File "G:\facelab\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
    debug=debug,
  File "G:\facelab\_internal\DeepFaceLab\models\ModelBase.py", line 200, in __init__
    self.on_initialize()
  File "G:\facelab\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 619, in on_initialize
    model.init_weights()
  File "G:\facelab\_internal\DeepFaceLab\core\leras\layers\Saveable.py", line 104, in init_weights
    nn.init_weights(self.get_weights())
  File "G:\facelab\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 51, in init_weights
    nn.batch_set_value( [*zip(ca_tuples_w, nn.initializers.ca.generate_batch (ca_tuples))] )
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\__init__.py", line 18, in generate_batch
    return CAInitializerSubprocessor (data_list).run()
  File "G:\facelab\_internal\DeepFaceLab\core\joblib\SubprocessorBase.py", line 257, in run
    data = self.get_data(cli.host_dict)
  File "G:\facelab\_internal\DeepFaceLab\core\leras\initializers\CA.py", line 67, in get_data
    shape, dtype = self.data_list[idx]
TypeError: list indices must be integers or slices, not tuple

xuciyu

不懂帮顶

chenbujun

为什么用中文的，你告诉我为什么用中文的