尝试从Keras运行顺序模型时发生ValueError

问题描述

我正在尝试使用Keras构建NARX NN。我仍然不确定在LSTM神经元中使用参数 return_sequence = True ，但是，在我能确认之前，我需要使代码正常工作。当我尝试运行它时，出现以下消息：

ValueError: Error when checking input: expected lstm_84_input to have 3 dimensions,but got array with shape (6686,3)

请参阅下面的代码。运行 model.fit 命令时会引发错误。我的数据数据具有40101个时间步长x 6个特征（3个外部输入，3个系统响应）的形状。

import numpy as np
import pandas as pd
from sklearn.model_selection import TimeSeriesSplit
import tensorflow as tf
from tensorflow.keras import initializers

# --- main
data = 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','current']])
y_data = np.array(data.loc[:,['X','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,return_sequences = True))
    
    # 2nd hidder layer
    model.add(tf.keras.layers.LSTM(units=50,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]

解决方法

LSTM层需要在3维上输入：

(n_samples,time_steps,features)

您以以下格式传递了数据：

(n_samples,features)

由于您没有创建时间步的功能，因此最简单的解决方案是将输入更改为形状：

(40101,1,3)

伪造数据：

x_data = np.random.rand(40101,3)
y_data = np.random.rand(40101,3)

此外，您不应在Keras层的input_shape参数中传递样本数。只需使用此：

input_shape=(1,3)

这是经过纠正的代码（带有伪造的数据）：

import numpy as np
from sklearn.model_selection import TimeSeriesSplit
import tensorflow as tf
from tensorflow.keras import initializers
from tensorflow.keras.layers import *

x_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,return_sequences=True))

    # 2nd hidder layer
    model.add(LSTM(units=50,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]

如果您希望函数创建时间步，请使用以下方法：

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,target=np.random.rand(40101,len(x_data),5,True)[0].shape

(40096,3)

您丢失了5个数据点，因为在开始时您无法回顾过去的5个步骤。