Question

根据Udemy教程，我正在keras Spyder中实现LSTM网络。在教程视频中，代码正在运行，但是当我自己运行代码时，该步骤与教程视频代码完全相同，因此会出现以下错误：

检查目标时出错：预期density_26具有3维，但数组的形状为（1198，1）

它与Spyder的版本有关吗？ x_train的大小为(1198,60,1)，y_train的大小为(1198,)

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

#Importing the training set
dataset_train = pd.read_csv('E:\\downloads_1\\Recurrent_Neural_Networks\\Google_Stock_Price_Train.csv')
training_set = dataset_train.iloc[:,1:2].values
#Feature Scaling 
from sklearn.preprocessing import MinMaxScaler
sc = MinMaxScaler(feature_range=(0,1))
training_set_scaled = sc.fit_transform(training_set)
#Creating a Data Structure with 60 timesteps and 1 output
x_train = []
y_train = []
for i in range(60,1258):
    x_train.append(training_set_scaled[i-60:i , 0])
    y_train.append(training_set_scaled[i , 0])
x_train , y_train = np.array(x_train) , np.array(y_train)

#Reshaping
x_train = np.reshape(x_train , (x_train.shape[0],x_train.shape[1], 1))



#Part 2_Building the Rnn

#importing te keras Libraries and Packages
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import LSTM


#initializing the RNN
regressor = Sequential()

#Adding the first layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True, input_shape = (x_train.shape[1], 1)))
regressor.add(Dropout(0.2))

#Adding the second layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True))
regressor.add(Dropout(0.2))

#Adding the third layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True))
regressor.add(Dropout(0.2))

#Adding the fourth layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True))
regressor.add(Dropout(0.2))

#Adding the output layer
regressor.add(Dense(units = 1))

#compiling the RNN
regressor.compile(optimizer= 'adam',  loss = 'mean_squared_error')

#Fitting the RNN TO the training set`enter code here`
regressor.fit(x_train, y_train, epochs = '100', batch_size = 32 )

Answer 1

您的LSTM返回一个序列（即return_sequences=True）。因此，您的最后一个LSTM层返回一个(batch_size, timesteps, 50)大小的3-D张量。然后，密集层返回一个3-D预测（即(batch_size, time steps, 1)）数组。

但是看来您正在输入二维输入作为输出（即1192x1）。因此，该模型必须为(1192, 60, 1)数组，模型才能使用标签。

这确实取决于您的问题。另一个选择是，如果每个数据点实际上只有1个输出值，则需要在最后一个LSTM上使用return_sequences=False。

#initializing the RNN
regressor = Sequential()

#Adding the first layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True, input_shape = (x_train.shape[1], 1)))
regressor.add(Dropout(0.2))

#Adding the second layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True))
regressor.add(Dropout(0.2))

#Adding the third layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= True))
regressor.add(Dropout(0.2))

#Adding the fourth layer LSTM and some Dropout Regularisations
regressor.add(LSTM(units = 50, return_sequences= False))
regressor.add(Dropout(0.2))

PS：同样要注意的是，您的Dense层实际上是3-D的。如果您要这样做，那很好。但是，在时序模型中使用Dense层的典型方式是使用TimeDistributed层，如下所示。

regressor.add(TimeDistirbuted(Dense(units = 1)))

keras中的LSTM input_shape

1 个答案: