LSTM inside RecurrentModel

[cpernoud]

Thanks for this great package! I've looked over your documentation and it certainly seems like this should work and I could use some help. I'm probably missing that I need to control the timestep in some way. I saw the nested code, but I think I'm getting tripped up on the Functional version. Here's the toy code:

import recurrentshop
import numpy
import keras.layers
from keras.layers import Dense, Input, LSTM
from keras.models import Model

prior_out = Input(batch_shape=(1,1,5),name='prior_out')
main_input = Input(batch_shape=(1,1,5),name='main_input')
added_layer = keras.layers.add([prior_out,main_input])
# hidden = LSTM(10,stateful=True,return_sequences=False,name='hidden')(added_layer)
hidden = recurrentshop.cells.LSTMCell(10)(added_layer)
out = Dense(5,name='out')(hidden)
rnn = recurrentshop.RecurrentModel(input=main_input, initial_states=prior_out, output=out, final_states=out)
rnn_input = Input(batch_shape=(1,1,5),name='rnn_input')
rnn_output = rnn(rnn_input)
model = Model(inputs=rnn_input,outputs=rnn_output)
model.compile(optimizer='adam',loss='mae')
print model.predict(numpy.random.random((3,1,5)),batch_size=1)

And I get this error:
ValueError: Operands could not be broadcast together with shapes (0,) (10,)

Thanks again for the help!

[farizrahman4u]

import recurrentshop
import numpy
import keras.layers
from keras.layers import Dense, Input, LSTM
from keras.models import Model

prior_out = Input(batch_shape=(1,5),name='prior_out')
main_input = Input(batch_shape=(1,5),name='main_input')
h_tm1 = Input(batch_shape=(1, 10))
c_tm1 = Input(batch_shape=(1, 10))
added_layer = keras.layers.add([prior_out,main_input])
# hidden = LSTM(10,stateful=True,return_sequences=False,name='hidden')(added_layer)
hidden, h, c = recurrentshop.cells.LSTMCell(10)([added_layer, h_tm1, c_tm1])
out = Dense(5,name='out')(hidden)
rnn = recurrentshop.RecurrentModel(input=main_input, initial_states=[prior_out, h_tm1, c_tm1], output=out, final_states=[out, h, c])
rnn_input = Input(batch_shape=(1,1,5),name='rnn_input')
rnn_output = rnn(rnn_input)
model = Model(inputs=rnn_input,outputs=rnn_output)
model.compile(optimizer='adam',loss='mae')
print model.predict(numpy.random.random((3,1,5)),batch_size=1)

[cpernoud]

Thanks @farizrahman4u , and there it was right on the front page, I just wasn't getting what it was doing.