我正在尝试使用Keras构建一个NARX神经网络。我对LSTM神经元中参数return_sequence=True的使用还不完全确定，但在我检查这个问题之前，我需要让代码先运行起来。当我尝试运行它时，收到了以下消息：
ValueError: Error when checking input: expected lstm_84_input to have 3 dimensions, but got array with shape (6686, 3)
请查看下面的代码。错误是在运行model.fit命令时引发的。我的数据形状为40101个时间步 x 6个特征（3个外生输入，3个系统响应）。
import numpy as npimport pandas as pdfrom sklearn.model_selection import TimeSeriesSplitimport tensorflow as tffrom tensorflow.keras import initializers# --- maindata = pd.read_excel('example.xlsx',usecols=['wave','wind','current','X','Y','RZ'])data.plot(subplots=True, figsize=[15,10])x_data = np.array(data.loc[:,['wave','wind','current']])y_data = np.array(data.loc[:,['X','Y','RZ']])timeSeriesCrossValidation = TimeSeriesSplit(n_splits=5)for train, validation in timeSeriesCrossValidation.split(x_data, y_data): # create model model = tf.keras.models.Sequential() # input layer model.add(tf.keras.layers.LSTM(units=50, input_shape=(40101,3), dropout=0.01, recurrent_dropout=0.2, kernel_initializer=initializers.RandomNormal(mean=0,stddev=.5), bias_initializer=initializers.Zeros(), return_sequences = True)) # 1st hidden layer model.add(tf.keras.layers.LSTM(units=50, dropout=0.01, recurrent_dropout=0.2, kernel_initializer=initializers.RandomNormal(mean=0,stddev=.5), bias_initializer=initializers.Zeros(), return_sequences = True)) # 2nd hidder layer model.add(tf.keras.layers.LSTM(units=50, dropout=0.01, recurrent_dropout=0.2, kernel_initializer=initializers.RandomNormal(mean=0,stddev=.5), bias_initializer=initializers.Zeros(), return_sequences = False)) # output layer model.add(tf.keras.layers.Dense(3)) model.compile(loss='mse',optimizer='nadam',metrics=['accuracy']) model.fit(x_data[train], y_data[train], verbose=2, batch_size=None, epochs=10, validation_data=(x_data[validation], y_data[validation]) #callbacks=early_stop ) prediction = model.predict(x_data[validation]) y_validation = y_data[validation]回答：
LSTM层需要三维的输入：
(n_samples, time_steps, features)您传递的数据格式为：
(n_samples, features)由于您没有创建时间步的函数，最简单的解决方案是将输入形状更改为：
(40101, 1, 3)伪数据示例：
x_data = np.random.rand(40101, 1, 3)y_data = np.random.rand(40101, 3)此外，您不应该在Keras层的input_shape参数中传递样本数量。请使用以下格式：
input_shape=(1, 3)因此，这里是修正后的代码（使用伪数据）：
import numpy as npfrom sklearn.model_selection import TimeSeriesSplitimport tensorflow as tffrom tensorflow.keras import initializersfrom tensorflow.keras.layers import *x_data = np.random.rand(40101, 1, 3)y_data = np.random.rand(40101, 3)timeSeriesCrossValidation = TimeSeriesSplit(n_splits=5)for train, validation in timeSeriesCrossValidation.split(x_data, y_data): # create model model = tf.keras.models.Sequential() # input layer model.add(LSTM(units=5, input_shape=(1, 3), dropout=0.01, recurrent_dropout=0.2, kernel_initializer=initializers.RandomNormal(mean=0, stddev=.5), bias_initializer=initializers.Zeros(), return_sequences=True)) # 1st hidden layer model.add(LSTM(units=5, dropout=0.01, recurrent_dropout=0.2, kernel_initializer=initializers.RandomNormal(mean=0, stddev=.5), bias_initializer=initializers.Zeros(), return_sequences=True)) # 2nd hidder layer model.add(LSTM(units=50, dropout=0.01, recurrent_dropout=0.2, kernel_initializer=initializers.RandomNormal(mean=0, stddev=.5), bias_initializer=initializers.Zeros(), return_sequences=False)) # output layer model.add(tf.keras.layers.Dense(3)) model.compile(loss='mse', optimizer='nadam', metrics=['accuracy']) model.fit(x_data[train], y_data[train], verbose=2, batch_size=None, epochs=1, validation_data=(x_data[validation], y_data[validation]) # callbacks=early_stop ) prediction = model.predict(x_data[validation]) y_validation = y_data[validation]如果您需要一个创建时间步的函数，请使用以下函数：
def multivariate_data(dataset, target, start_index, end_index, history_size, target_size, step, single_step=False): data = [] labels = [] start_index = start_index + history_size if end_index is None: end_index = len(dataset) - target_size for i in range(start_index, end_index): indices = range(i-history_size, i, step) data.append(dataset[indices]) if single_step: labels.append(target[i+target_size]) else: labels.append(target[i:i+target_size]) return np.array(data), np.array(labels)它将为您提供正确的形状，例如：
multivariate_data(dataset=np.random.rand(40101, 3), target=np.random.rand(40101, 3), 0, len(x_data), 5, 0, 1, True)[0].shape(40096, 5, 3)您失去了5个数据点，因为在开始时您无法回顾过去5个步骤。
