ValueError:bucket_boundaries不能为空

问题描述

我正在克隆此repo,以尝试使用之前通过Google Colab在线收集的数据来实现“文本到语音模型”的算法,

!pip install numpy==1.11.1
!pip install tensorFlow==1.3
!pip install tqdm
!pip install matplotlib
!pip install scipy

那我做的是:

cd /content/gdrive/My Drive/dc_tts

然后

#!python prepo.py
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:458: FutureWarning: Passing (type,1) or '1type' as a synonym of type is deprecated; in a future version of numpy,it will be understood as (type,(1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8",np.int8,1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:459: FutureWarning: Passing (type,)type'.
  _np_quint8 = np.dtype([("quint8",np.uint8,1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:460: FutureWarning: Passing (type,)type'.
  _np_qint16 = np.dtype([("qint16",np.int16,1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:461: FutureWarning: Passing (type,)type'.
  _np_quint16 = np.dtype([("quint16",np.uint16,1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:462: FutureWarning: Passing (type,)type'.
  _np_qint32 = np.dtype([("qint32",np.int32,1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:465: FutureWarning: Passing (type,)type'.
  np_resource = np.dtype([("resource",np.ubyte,1)])
100% 1/1 [00:03<00:00,3.65s/it]

现在我正尝试与之训练模型

!python train.py 1

但出现此错误

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:458: FutureWarning: Passing (type,1)])
Traceback (most recent call last):
  File "train.py",line 141,in <module>
    g = Graph(num=num); print("Training Graph loaded")
  File "train.py",line 40,in __init__
    self.L,self.mels,self.mags,self.fnames,self.num_batch = get_batch()
  File "/content/gdrive/My Drive/dc_tts/data_load.py",line 104,in get_batch
    dynamic_pad=True)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/contrib/training/python/training/bucket_ops.py",line 368,in bucket_by_sequence_length
    raise ValueError("bucket_boundaries must not be empty")
ValueError: bucket_boundaries must not be empty

进行一些谷歌搜索和调试,即使使用外部实用程序或更改长度,我也找不到任何信息

解决方法

暂无找到可以解决该程序问题的有效方法,小编努力寻找整理中!

如果你已经找到好的解决方法,欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@)