I am trying to predict the power (label) generated by solar intensity (feature) through time series data. So, I am trying to create a seq2seq model without attention mechanism.(I'm trying to predict the 11th label with the past 10 days' feautre.) However, I need encoder_inputs, decoder_inputs, and decoder_outputs as shown in the code below. I know that encoder_inputs needs to contain the data of the past 10 days. What form should I put in decoder_inputs and decoder_outputs?
# Define an input sequence and process it.
encoder_inputs = keras.Input(shape=(None, num_encoder_tokens))
encoder = keras.layers.LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = keras.Input(shape=(None, num_decoder_tokens))
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = keras.layers.LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs, initial_state=encoder_states)
decoder_dense = keras.layers.Dense(num_decoder_tokens, activation="softmax")
decoder_outputs = decoder_dense(decoder_outputs)
# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = keras.Model([encoder_inputs, decoder_inputs], decoder_outputs)
I searched a lot of codes, but most of them didn't find predicting labels using features.
