Question

我正在尝试导入预训练的张量流模型（教程中的默认声音识别）并且我一直收到此错误。

我尝试使用检查点文件和.pb文件导入，作为初学者，我不知道这个错误。任何帮助将不胜感激！

我在Debian和Windows 10，python3.5以及具有多个tensorflow版本的python 3.6上试过这个。

Traceback (most recent call last):
  File "C:\tmp\speech_commands_train\Ztest.py", line 4, in <module>
    saver = tf.train.import_meta_graph('conv.ckpt-18000.meta')
  File "C:\Dev\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1927, in import_meta_graph
    **kwargs)
  File "C:\Dev\Python36\lib\site-packages\tensorflow\python\framework\meta_graph.py", line 741, in import_scoped_meta_graph
    producer_op_list=producer_op_list)
  File "C:\Dev\Python36\lib\site-packages\tensorflow\python\util\deprecation.py", line 432, in new_func
    return func(*args, **kwargs)
  File "C:\Dev\Python36\lib\site-packages\tensorflow\python\framework\importer.py", line 457, in import_graph_def
    _RemoveDefaultAttrs(op_dict, producer_op_list, graph_def)
  File "C:\Dev\Python36\lib\site-packages\tensorflow\python\framework\importer.py", line 227, in _RemoveDefaultAttrs
    op_def = op_dict[node.op]
KeyError: 'DecodeWav'

这是我用来导入的代码：

import tensorflow as tf
sess = tf.Session()
saver = tf.train.import_meta_graph('conv.ckpt-18000.meta')
saver.restore(sess, tf.train.latest_checkpoint('./'))

Tensorflow声音识别教程给出错误：op_def = op_dict [node.op] KeyError：＆＃39; DecodeWav＆＃39;

0 个答案: