Problem with one example found in Stackoverflow

[malinthasa]

Hi,

Thank you very much for writing the library.

I was looking using non-sequential input to my LSTM and found this code snippet from STOF.

import numpy as np

from tensorflow.keras.models import Model
from tensorflow.keras.layers import LSTM, Dense, Input
from cond_rnn import ConditionalRNN

inputs = Input(name='in',shape=(5,5)) # Each observation has 5 dimensions à 5 time-steps each
x = Dense(64)(inputs)

inputs_aux = Input(name='in_aux', shape=[5]) # For each of the 5 dimensions, a non-time-series observation too
x = ConditionalRNN(7, cell='LSTM', cond=inputs_aux)(x)

predictions = Dense(1)(x)
model = Model(inputs=[inputs, inputs_aux], outputs=predictions)
#model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop', loss='mean_squared_error', metrics=['mse'])
data = np.random.standard_normal([100,5,5]) # Sample of 100 observations with 5 dimensions à 5 time-steps each
data_aux = np.random.standard_normal([100,5]) # Sample of 100 observations with 5 dimensions à only 1 non-time-series value each
labels = np.random.standard_normal(size=[100]) # For each of the 100 obs., a corresponding (single) outcome variable

model.fit([data,data_aux], labels)

I just tried to run it but got an error

TypeError: ('Keyword argument not understood:', 'cond')

According to the API the condition input should be like follows

outputs = cond_rnn.ConditionalRNN(units=NUM_CELLS, cell='GRU')([inputs, cond])

but I am not clear why this sample code uses the condition as parameter. Can you help me to correct the above code. Thank you very much for your time.

[malinthasa]

I tried

x = ConditionalRNN(units=7, cell='LSTM')([x, inputs_aux])

and ended up with AttributeError: 'tuple' object has no attribute 'layer' error

[philipperemy]

Update the cond-rnn lib and use this code:

import numpy as np

from tensorflow.keras.models import Model
from tensorflow.keras.layers import LSTM, Dense, Input
from cond_rnn import ConditionalRNN

inputs = Input(name='in',shape=(5,5)) # Each observation has 5 dimensions à 5 time-steps each
x = Dense(64)(inputs)

inputs_aux = Input(name='in_aux', shape=[5]) # For each of the 5 dimensions, a non-time-series observation too
x = ConditionalRNN(7, cell='LSTM')([x,inputs_aux]) # Updated Syntax for cond_rnn v2.1
# x = ConditionalRNN(7, cell='LSTM', cond=inputs_aux)(x) # Syntax for cond_rnn in some version before v2.1

predictions = Dense(1)(x)
model = Model(inputs=[inputs, inputs_aux], outputs=predictions) # With this fix, [inputs, inputs_aux], it now works, solving the issue
#model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop', loss='mean_squared_error', metrics=['mse'])
data = np.random.standard_normal([100,5,5]) # Sample of 100 observations with 5 dimensions à 5 time-steps each
data_aux = np.random.standard_normal([100,5]) # Sample of 100 observations with 5 dimensions à only 1 non-time-series value each
labels = np.random.standard_normal(size=[100]) # For each of the 100 obs., a corresponding (single) outcome variable

model.fit([data,data_aux], labels)

[malinthasa]

Thank you

[philipperemy]

@malinthasa welcome :)