CNTK-106 Part A:ValueError

教材网址：https://cntk.ai/pythondocs/CNTK_106A_LSTM_Timeseries_with_Simulated_Data.html

编程系统：windows7

开发语言： python2.7

      在运行CNTK-106 PartA出现了错误：

Traceback (most recent calllast):

File"E:\ProgramLib\Python\CNTK\CNTK-106-PartA-LSTM.py",line 171, in trainer.train_minibatch({x:x1, l: y1})

File"C:\Python27\lib\site-packages\cntk\train\trainer.py",line 184, in

train_minibatch device) File"C:\Python27\lib\site-packages\cntk\cntk_py.py",line 2856, in

train_minibatch

return _cntk_py.Trainer_train_minibatch(self,*args)

ValueError: The trailing dimensions of the Valueshape '[100]' do not match the Variable 'Input('y', [#], [1])'shape '[1]'.

解决方法：

1.原因：输入的Y，数据格式错误，应该变形成X的格式。

X:

[[0.02000067]

[0.0299985 ]

[0.03999333]

[0.04998416]

[0.05997 ]]

Y: [0.08988751 0.099843370.10978924]

应该把Y变成形如：

[ [0.08988751]

[0.09984337]

[0.10978924]]

2.修改的代码：

def generate_data(fct, x, time_steps,time_shift):

"""

generate sequences to feed to rnn for fct(x)

"""

    data = fct(x)

    if not isinstance(data, pd.DataFrame):

    data = pd.DataFrame(dict(a = data[0:len(data) - time_shift],

                                               b = data[time_shift:]))  

    rnn_x = []

    for i in range(len(data) - time_steps + 1):

        rnn_x.append(data['a'].iloc[i: i + time_steps].as_matrix())

        rnn_x = np.array(rnn_x)

    # Reshape or rearrange the data from row to columns

    # to be compatible with the input needed by the LSTM model

#which expects 1 floatper time point in a given batch

    rnn_x = rnn_x.reshape(rnn_x.shape + (1,))

    rnn_y = data['b'].values

    rnn_y = rnn_y[time_steps - 1 :]

    rnn_y = rnn_y.reshape(rnn_y.shape + (1,))  # 增加该行代码，将Y变成X样式

    return split_data(rnn_x), split_data(rnn_y)

修改后运行成功。