Python 检查模型输入时出错：预期 lstm_1_input 有 3 个维度，但得到的数组具有形状 (339732, 29)
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/44704435/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Error when checking model input: expected lstm_1_input to have 3 dimensions, but got array with shape (339732, 29)
提问by Saurav--
My input is simply a csv file with 339732 rows and two columns :
我的输入只是一个包含 339732 行和两列的 csv 文件：
- the first being 29 feature values, i.e. X
- the second being a binary label value, i.e. Y
- 第一个是 29 个特征值，即 X
- 第二个是二进制标签值，即 Y
I am trying to train my data on a stacked LSTM model:
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)
This throws the error:
这会引发错误：
Traceback (most recent call last): File "first_approach.py", line 80, in model.fit(X_train, y_train, batch_size = 400, epochs = 20, verbose = 1)
ValueError: Error when checking model input: expected lstm_1_input to have 3 dimensions, but got array with shape (339732, 29)
回溯（最近一次调用）：文件“first_approach.py”，第 80 行，在 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 有 3 个维度，但得到了具有形状的数组 (339732, 29)
I tried reshaping my input using X_train.reshape((1,339732, 29))but it did not work showing error:
我尝试使用重塑我的输入，X_train.reshape((1,339732, 29))但它没有工作显示错误：
ValueError: Error when checking model input: expected lstm_1_input to have shape (None, 8, 29) but got array with shape (1, 339732, 29)
ValueError：检查模型输入时出错：预期 lstm_1_input 具有形状 (None, 8, 29) 但得到形状为 (1, 339732, 29) 的数组
How can I feed in my input to the LSTM ?
如何将我的输入输入到 LSTM 中？
回答by Saurav--
Setting timesteps = 1(since, I want one timestep for each instance) and reshaping the X_train and X_test as:
设置timesteps = 1（因为我希望每个实例都有一个时间步长）并将 X_train 和 X_test 重塑为：
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]))
This worked!
这有效！
回答by shadi
For timesteps != 1, you can use the below function (adapted from here)
对于timesteps != 1，您可以使用以下功能（改编自此处）
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)
Examples
例子
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]]))
回答by Ashok Kumar Jayaraman
Reshape input for LSTM:
重塑 LSTM 的输入：
X = array([[10, 20, 30], [40, 50, 60], [70, 80, 90]])
X_train = X.reshape(1, 3, 3) # X.reshape(samples, timesteps, features)
