我正在尝试在某些时间序列集上运行 RNN/LSTM 网络。值得一提的是,时间序列正在分类。我有大约 600 个不同的时间序列,每个序列都有 930 个带有特征的时间步长。我已将数据结构化为 numpy 3D 数组,其结构如下:
X = [666 observations/series, 930 timesteps in each observation, 15 features]
Y = [666 observations/series, 930 timesteps in each observation, 2 features]
对于训练和验证数据,我将数据分成 70/30。所以 Train_X = [466, 930, 15] 和 Train_Y = [200, 930, 2]。
我的网络收到一个错误,表示它期望输入为二维,并且得到一个形状为 (466, 930, 2) 的数组。我的代码如下:
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Bidirectional
Train_X = new_ped_data[0:466]
Test_X = new_ped_data[466:]
Train_Y = new_ped_valid_data[0:466]
Test_Y = new_ped_valid_data[466:]
model = Sequential()
model.add(Bidirectional(LSTM(20, return_sequences=True),
input_shape=Train_X.shape[1:]))
model.add(Bidirectional(LSTM(10)))
model.add(Dense(5))
model.compile(loss='mae',
optimizer='rmsprop')
model.fit(Train_X, Train_Y, epochs = 30, batch_size = 32,
validation_data =(Test_X, Test_Y))
我只是想让模型运行起来。一旦完成,我将调整架构和拟合参数。我应该提到,其中一个分类输出可能不是必需的。关于如何设置架构,以便在输入时间序列时我将获得每个时间步长的网络分类值,有什么建议吗?
Error was: ValueError: Error when checking target: expected dense_9 to
have 2 dimensions, but got array with shape (466, 930, 2)