I'm trying to adapt the example of a cnn-lstm for a univariate time series from a tutorial blog to an airline passenger problem written with LSTM

Question

I'm trying to adapt the example of a cnn-lstm for a univariate time series from https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/ to an airline passenger problem written in LSTM,in another blog https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural.networks-python-keras/ but receievd the following error

This the entire code and error message received

# LSTM for international airline passengers problem with window regression framing
import numpy
import matplotlib.pyplot as plt
import pandas
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Flatten
from keras.layers import TimeDistributed
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
 
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
# convert an array of values into a dataset matrix
def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back), 0]
        dataX.append(a)
        dataY.append(dataset[i + look_back, 0])
    return numpy.array(dataX), numpy.array(dataY)
# fix random seed for reproducibility
numpy.random.seed(7)
# load the dataset
dataframe = pandas.read_csv('dummy_timeseries.csv' , usecols=[1],
engine= 'python' , skipfooter=3)
dataset = dataframe.values
dataset = dataset.astype('float32' )
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# split into train and test sets
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
# reshape into X=t and Y=t+1
look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# reshape input to be [samples, time steps, features]

n_features = 1
trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
# define model
model = Sequential()
model.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'),input_shape=(None,look_back, n_features)))
model.add(TimeDistributed(MaxPooling1D(pool_size=2)))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(50, activation='relu'))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# invert predictions
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print( 'Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print( 'Test Score: %.2f RMSE' % (testScore))
# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
# shift test predictions for plotting
testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict
# plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()


                              Error Message
Epoch 1/100
Traceback (most recent call last):

  File "C:\Users\cisco4gud\Desktop\spider\LSTMwindowairline.py", line 62, in <module>
    model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py", line 108, in _method_wrapper
    return method(self, *args, **kwargs)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1098, in fit
    tmp_logs = train_function(iterator)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 780, in __call__
    result = self._call(*args, **kwds)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 823, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 697, in _initialize
    *args, **kwds))

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\function.py", line 2855, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\function.py", line 3213, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\function.py", line 3075, in _create_graph_function
    capture_by_value=self._capture_by_value),

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\framework\func_graph.py", line 986, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 600, in wrapped_fn
    return weak_wrapped_fn().__wrapped__(*args, **kwds)

  File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\framework\func_graph.py", line 973, in wrapper
    raise e.ag_error_metadata.to_exception(e)

ValueError: in user code:

    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function  *
        return step_function(self, iterator)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step  **
        outputs = model.train_step(data)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:747 train_step
        y_pred = self(x, training=True)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:976 __call__
        self.name)
    C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:180 assert_input_compatibility
        str(x.shape.as_list()))

    ValueError: Input 0 of layer sequential_46 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [1, 1, 3]

Answer 1

Try to change this line (remove batch dimension from input shape):

model.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(look_back, n_features)))

Answer 2

I changed the  reshape input from [samples, time steps, features] to  [samples,subsequence, time steps, features] and the code for that section changes to 


n_features = 1
n_seq = 1
n_steps = 3
trainX = trainX.reshape((trainX.shape[0], n_seq, n_steps, n_features))
testX = testX.reshape((testX.shape[0], n_seq, n_steps, n_features))