I try to reshape and concat some output to compleate original input and use it in next stage of my model. Dimension seem to match but I get this error:
Concatenate(axis=2)([tensor_input2, out_first_try])
*** ValueError: A `Concatenate` layer requires inputs with matching
shapes except for the concat axis. Got inputs shapes: [(64, 10, 8), [(),
(), ()]]
I also try :
tf.concat([tensor_input2, out_first_try], 2)
with this error:
tf.concat([tensor_input2, out_first_try], 2)
*** ValueError: Shape must be rank 3 but is rank 1 for '{{node
tf.concat/concat}} = ConcatV2[N=2, T=DT_FLOAT, Tidx=DT_INT32]
(Placeholder, tf.concat/concat/values_1, tf.concat/concat/axis)' with
input shapes: [64,10,8], [3], [].
The cause seem to be the same but I can't figure how to deal with that,
# tensor_input1 = [64,365,9]
tensor_input1 = Input(batch_size=batch, shape=(X.shape[1],
X.shape[2]), name='input1')
# tensor_input2 = [64,10,8]
tensor_input2 = Input(batch_size=batch, shape=(X2.shape[1],
X2.shape[2]), name='input2')
extractor = CuDNNLSTM(100, return_sequences=False,
stateful=False, name='LSTM1')(tensor_input2)
extractor = Dropout(rate = .2)(extractor)
extractor = Dense(100, activation='softsign')(extractor)
out_1 = Dense(10, activation='linear')(extractor2)
# add a dimension to out_1 [64,10] to fit tensor_input2
out_first_try = tf.expand_dims(out_1, axis=2).shape.as_list()
# concat in 3d dim the output to the original input
# tensor_input2 =[64,10,8]
# out_first_try, after tf.expend [64,10,1]
forcast_input = Concatenate(axis=2)([tensor_input2,
out_first_try])
# forcast_input expected size [64,10,9]
# finaly concat tensor_input1, new tensor_input2 side to side
allin_input = Concatenate(axis=1)([tensor_input1, forcast_input])
# allin_input expected size [64,365 10,9]
extractor2 = CuDNNLSTM(100, return_sequences=False,
stateful=False, name='LSTM1')(allin_input )
...
CodePudding user response:
Concatenating a tensor with a list will not work. So, maybe try something like this:
out_first_try = tf.expand_dims(out_1, axis=2)
forcast_input = Concatenate(axis=2)([tensor_input2, out_first_try])
Note that I have removed shape.as_list()
because, as the name suggests, it returns the shape of a tensor as a list. You can verify that with this example:
import tensorflow as tf
out_1 = tf.random.normal((5, 10))
out_first_try = tf.expand_dims(out_1, axis=2).shape.as_list()
tf.print(type(out_first_try))
#<class 'list'>