检查模型输入时出错:预期lstm_1_input具有3个维度,但是具有形状的数组(339732,29)

时间:2017-06-22 16:04:18

标签: python keras lstm recurrent-neural-network valueerror

我的输入只是一个包含339732行和两列的csv文件:

  • 第一个是29个特征值,即X
  • 第二个是二进制标签值,即Y

我正在尝试在堆叠的LSTM模型上训练我的数据:

data_dim = 29
timesteps = 8
num_classes = 2

model = Sequential()
model.add(LSTM(30, return_sequences=True,
               input_shape=(timesteps, data_dim)))  # returns a sequence of vectors of dimension 30
model.add(LSTM(30, return_sequences=True))  # returns a sequence of vectors of dimension 30
model.add(LSTM(30))  # return a single vector of dimension 30
model.add(Dense(1, activation='softmax'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

model.summary()
model.fit(X_train, y_train, batch_size = 400, epochs = 20, verbose = 1)

这会引发错误:

  

追踪(最近一次通话):     文件" first_approach.py​​",第80行,in       model.fit(X_train,y_train,batch_size = 400,epochs = 20,verbose = 1)

     

ValueError:检查模型输入时出错:预期lstm_1_input为   有3个尺寸,但有阵形(339732,29)

我尝试使用X_train.reshape((1,339732, 29))重塑我的输入,但它无法显示错误:

  

ValueError:检查模型输入时出错:预期lstm_1_input为   有形状(无,8,29)但有阵形(1,339732,29)

如何输入我对LSTM的输入?

3 个答案:

答案 0 :(得分:20)

设置timesteps = 1(因为,我希望每个实例有一个时间步长)并将X_train和X_test重新整形为:

import numpy as np
X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1]))
X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1]))

这很有用!

答案 1 :(得分:4)

对于timesteps != 1,您可以使用以下功能(改编自here

import numpy as np
def create_dataset(dataset, look_back=1):
  dataX, dataY = [], []
  for i in range(len(dataset)-look_back+1):
    a = dataset[i:(i+look_back), :]
    dataX.append(a)
    dataY.append(dataset[i + look_back - 1, :])
  return np.array(dataX), np.array(dataY)

实施例

X = np.reshape(range(30),(3,10)).transpose()
array([[ 0, 10, 20],
       [ 1, 11, 21],
       [ 2, 12, 22],
       [ 3, 13, 23],
       [ 4, 14, 24],
       [ 5, 15, 25],
       [ 6, 16, 26],
       [ 7, 17, 27],
       [ 8, 18, 28],
       [ 9, 19, 29]])

create_dataset(X, look_back=1 )
(array([[[ 0, 10, 20]],
       [[ 1, 11, 21]],
       [[ 2, 12, 22]],
       [[ 3, 13, 23]],
       [[ 4, 14, 24]],
       [[ 5, 15, 25]],
       [[ 6, 16, 26]],
       [[ 7, 17, 27]],
       [[ 8, 18, 28]],
       [[ 9, 19, 29]]]),
array([[ 0, 10, 20],
       [ 1, 11, 21],
       [ 2, 12, 22],
       [ 3, 13, 23],
       [ 4, 14, 24],
       [ 5, 15, 25],
       [ 6, 16, 26],
       [ 7, 17, 27],
       [ 8, 18, 28],
       [ 9, 19, 29]]))

create_dataset(X, look_back=3)
(array([[[ 0, 10, 20],
        [ 1, 11, 21],
        [ 2, 12, 22]],
       [[ 1, 11, 21],
        [ 2, 12, 22],
        [ 3, 13, 23]],
       [[ 2, 12, 22],
        [ 3, 13, 23],
        [ 4, 14, 24]],
       [[ 3, 13, 23],
        [ 4, 14, 24],
        [ 5, 15, 25]],
       [[ 4, 14, 24],
        [ 5, 15, 25],
        [ 6, 16, 26]],
       [[ 5, 15, 25],
        [ 6, 16, 26],
        [ 7, 17, 27]],
       [[ 6, 16, 26],
        [ 7, 17, 27],
        [ 8, 18, 28]],
       [[ 7, 17, 27],
        [ 8, 18, 28],
        [ 9, 19, 29]]]),
array([[ 2, 12, 22],
       [ 3, 13, 23],
       [ 4, 14, 24],
       [ 5, 15, 25],
       [ 6, 16, 26],
       [ 7, 17, 27],
       [ 8, 18, 28],
       [ 9, 19, 29]]))

答案 2 :(得分:2)

为LSTM重塑输入:

X = array([[10, 20, 30], [40, 50, 60], [70, 80, 90]])
X_train = X.reshape(1, 3, 3) # X.reshape(samples, timesteps, features)