为什么 model.predict 给出 3 个输出？

Question

I'm trying to use Keras to make predictions on a univariate time series.

The NN model looks like

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d (Conv1D)              (None, None, 25)          150       
_________________________________________________________________
lstm (LSTM)                  (None, None, 1024)        4300800   
_________________________________________________________________
dropout (Dropout)            (None, None, 1024)        0         
_________________________________________________________________
lstm_1 (LSTM)                (None, None, 1024)        8392704   
_________________________________________________________________
dropout_1 (Dropout)          (None, None, 1024)        0         
_________________________________________________________________
lstm_2 (LSTM)                (None, None, 1024)        8392704   
_________________________________________________________________
dropout_2 (Dropout)          (None, None, 1024)        0         
_________________________________________________________________
lstm_3 (LSTM)                (None, None, 1024)        8392704   
_________________________________________________________________
dropout_3 (Dropout)          (None, None, 1024)        0         
_________________________________________________________________
dense (Dense)                (None, None, 1)           1025      
=================================================================
Total params: 29,480,087
Trainable params: 29,480,087
Non-trainable params: 0
_________________________________________________________________

My data is windowed using the previous 3 values of the series to predict the next. Thus my test dataset looks like

list(dataset.as_numpy_iterator())
[array([[[ 0.        ],
         [ 0.02346429],
         [ 0.04559132]],

        [[ 0.        ],
         [ 0.02161974],
         [ 0.13014923]],

        [[ 0.        ],
         [ 0.10623277],
         [-0.02918068]],

        [[ 0.        ],
         [-0.12240955],
         [-0.21869095]]])]

All well and good, but when I feed this to model.predict(dataset) the output it spits out is

array([[[ 0.01316399],
        [ 0.03728709],
        [ 0.06164959]],

       [[ 0.01316399],
        [ 0.03512047],
        [ 0.1292857 ]],

       [[ 0.01316399],
        [ 0.1172413 ],
        [-0.01671433]],

       [[ 0.01316399],
        [-0.10654409],
        [-0.16395506]]], dtype=float32)

and the shape for this example is (4, 3, 1)

I was expecting just to get a single predict for each triplet of input features, given the final layer of my NN is a Dense with a single unit. Why do I seem to have three outputs in the prediction for each training example?

Answer 1

In your last LSTM layer, set the argument return_sequences=False.

LSTM(..., return_sequences=False)