Keras LSTM Outputting Different Dimension than Expected

Question

I'm running a LSTM on fMRI data. Our input data comes in with input_shape (timesteps,features) =(495,359320) and label data (495,). I'm running into an issue with what the LSTM layer is outputting.

   MAX_SLIDER_VALUE=127
   EPOCHS=3
   BATCH_SIZE=1
   LOSS='mean_squared_error'
   OPTIMIZER='RMSprop'

   model=Sequential()
`  model.add(LSTM(units=MAX_SLIDER_VALUE,` activation=keras.layers.LeakyReLU(alpha=.025),dropout=.08,input_shape=(495,359320)))
   model.add(Dense(units=MAX_SLIDER_VALUE,activation='softmax'))``

   model.compile(loss=LOSS,optimizer=OPTIMIZER, metrics=['acc','mae']) 

   model.fit(np.array(train_subset_nii),np.array(train_subset_labels),
   epochs=EPOCHS,batch_size=BATCH_SIZE)

Checking the model's output layer using the pdb debugger shows the 0th layer output should be (127,) but I'm are getting a valueError where it is outputted as (495,).

model.layers[0].input_shape
(None, 495, 359320)

model.layers[0].output_shape
(None, 127)

model.layers[1].input_shape
(None, 127)

model.layers[1].output_shape
(None, 127)


ValueError: Error when checking target: expected dense_5 to have shape (127,) but got array with shape (495,)

Additional Note:

The code trains and runs if we change the output to match the number of time steps

MAX_SLIDER_VALUE=495

I'm trying to figure out whats causing the disparity between (127,) and (495,).

ian ian · Accepted Answer · 2019-03-03T02:17:29

LSTM default for return_sequences is False, so the LSTM layer will output only the last cell output -> (None (batch), units=MAX_SLIDER_VALUE). If you want to output (None, 495, MAX_SLIDER_VALUE), change return_sequences to True in the LSTM initialization (units does not have to be MAX_SLIDER_VALUE), and the Dense units to MAX_SLIDER_VALUE.

Keras LSTM Outputting Different Dimension than Expected

2 Answers