不兼容的形状：Tensorflow/Keras Sequential LSTM with Autoencoder

Question

I am trying to set up an LSTM Autoencoder/Decoder for time series data and continually get Incompatible shapes error when trying to train the model. Following steps and using toy data from this example . See below code and results. Note Tensorflow version 2.3.0.

Create data. Put data into sequences to temporalize for LSTM in the form of (samples, timestamps, features).

timeseries = np.array([[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9],
                       [0.1**3, 0.2**3, 0.3**3, 0.4**3, 0.5**3, 0.6**3, 0.7**3, 0.8**3, 0.9**3]]).transpose()

timeseries_df = pd.DataFrame(timeseries)

def create_sequenced_dataset(X, time_steps=10):
    Xs, ys = [], []  # start empty list
    for i in range(len(X) - time_steps):  # loop within range of data frame minus the time steps
        v = X.iloc[i:(i + time_steps)].values  # data from i to end of the time step
        Xs.append(v)
        ys.append(X.iloc[i + time_steps].values)

    return np.array(Xs), np.array(ys)  # convert lists into numpy arrays and return

X, y = create_sequenced_dataset(timeseries_df, time_steps=3)
timesteps = X.shape[1]
n_features = X.shape[2]

Create the LSTM model with autoencoder/decoder given by the Repeat Vector and attempt to train the model.

model = Sequential()
model.add(LSTM(128, input_shape=(timesteps, n_features), return_sequences=False))
model.add(RepeatVector(timesteps))
model.add(LSTM(128, return_sequences=True))
model.add(TimeDistributed(Dense(n_features)))
model.compile(optimizer='adam', loss='mse')
model.summary()

model.fit(X, y, epochs=10, batch_size=4)

Consistently get error:

tensorflow.python.framework.errors_impl.InvalidArgumentError:  Incompatible shapes: [4,3,2] vs. [4,2]
     [[node gradient_tape/mean_squared_error/BroadcastGradientArgs (defined at <ipython-input-9-56896428cea9>:1) ]] [Op:__inference_train_function_10833]

X looks like:

array([[[0.1  , 0.001],
        [0.2  , 0.008],
        [0.3  , 0.027]],
       [[0.2  , 0.008],
        [0.3  , 0.027],
        [0.4  , 0.064]],
       [[0.3  , 0.027],
        [0.4  , 0.064],
        [0.5  , 0.125]],
       [[0.4  , 0.064],
        [0.5  , 0.125],
        [0.6  , 0.216]],
       [[0.5  , 0.125],
        [0.6  , 0.216],
        [0.7  , 0.343]],
       [[0.6  , 0.216],
        [0.7  , 0.343],
        [0.8  , 0.512]]])

y looks like:

array([[0.4  , 0.064],
       [0.5  , 0.125],
       [0.6  , 0.216],
       [0.7  , 0.343],
       [0.8  , 0.512],
       [0.9  , 0.729]])

Answer 1

I hope the translator will correctly translate my idea. I also did not understand at first what the problem was, but then I read the definition of an autoencoder again. Since this is an autoencoder, we apply X to the input and output (y does not participate in the model in any way, since we are trying to determine the dependencies in the data X and then recreate them). Some have code on this topic (y = x.copy ()), while here it applies (model.fit (X, X, epochs = 300, batch_size = 5, verbose = 0)).

Answer 2

As the message clearly says, it's the shape issue which you are passing to the model for fit.

From the above data which you have given X is having the shape of (6, 3, 2) and Y is having the shape of (6, 2) which is incompatible.

Below is the modified code with the same input as per the example you have taken with X and Y having a shape (6,3,2) .

model = Sequential()
model.add(LSTM(128, input_shape=(timesteps, n_features), return_sequences=False))
model.add(RepeatVector(timesteps))
model.add(LSTM(128, return_sequences=True))
model.add(TimeDistributed(Dense(n_features)))
model.compile(optimizer='adam', loss='mse')
model.summary()  

model.fit(X,Y, epochs=10, batch_size=4)

Result:

Epoch 1/10
2/2 [==============================] - 0s 5ms/step - loss: 0.0069
Epoch 2/10
2/2 [==============================] - 0s 4ms/step - loss: 0.0065
Epoch 3/10
2/2 [==============================] - 0s 4ms/step - loss: 0.0065
Epoch 4/10
2/2 [==============================] - 0s 4ms/step - loss: 0.0062
Epoch 5/10
2/2 [==============================] - 0s 4ms/step - loss: 0.0059
Epoch 6/10
2/2 [==============================] - 0s 4ms/step - loss: 0.0053
Epoch 7/10
2/2 [==============================] - 0s 5ms/step - loss: 0.0048
Epoch 8/10
2/2 [==============================] - 0s 5ms/step - loss: 0.0046
Epoch 9/10
2/2 [==============================] - 0s 5ms/step - loss: 0.0044
Epoch 10/10
2/2 [==============================] - 0s 6ms/step - loss: 0.0043
<tensorflow.python.keras.callbacks.History at 0x7ff352f9ccf8>