How to concatenate two layers in keras?
I have an example of a neural network with two layers. The first layer takes two arguments and has one output. The second should take one argument as result of the first layer and one additional argument. It should looks like this:
x1 x2 x3
/ /
y1 /
/
y2
So, I'd created a model with two layers and tried to merge them but it returns an error: The first layer in a Sequential model must get an "input_shape" or "batch_input_shape" argument. on the line result.add(merged).
Model:
first = Sequential()
first.add(Dense(1, input_shape=(2,), activation='sigmoid'))
second = Sequential()
second.add(Dense(1, input_shape=(1,), activation='sigmoid'))
result = Sequential()
merged = Concatenate([first, second])
ada_grad = Adagrad(lr=0.1, epsilon=1e-08, decay=0.0)
result.add(merged)
result.compile(optimizer=ada_grad, loss=_loss_tensor, metrics=['accuracy'])
Below are some keras concatenate examples, the main reason for this error is the result defined as Sequential() is just a container for the model and you have not defined input for it.
It looks like you’re trying to build a set result to take the third input x3.
Improvised code for your problem:
first = Sequential()
first.add(Dense(1, input_shape=(2,), activation='sigmoid'))
second = Sequential()
second.add(Dense(1, input_shape=(1,), activation='sigmoid'))
third = Sequential()
# provide the input to result with will be your x3
third.add(Dense(1, input_shape=(1,), activation='sigmoid'))
#then add a few more layers to first and second.
# concatenate them
merged = Concatenate([first, second])
# then concatenate the two outputs
result = Concatenate([merged, third])
ada_grad = Adagrad(lr=0.1, epsilon=1e-08, decay=0.0)
result.compile(optimizer=ada_grad, loss='binary_crossentropy',
metrics=['accuracy'])
You can try another way of building a model that this type of input structure would be to use the functional API.
For example:
from keras.models import Model
from keras.layers import Concatenate, Dense, LSTM, Input, concatenate
from keras.optimizers import Adagrad
first_input = Input(shape=(2, ))
first_dense = Dense(1, )(first_input)
second_input = Input(shape=(2, ))
second_dense = Dense(1, )(second_input)
merge_one = concatenate([first_dense, second_dense])
third_input = Input(shape=(1, ))
merge_two = concatenate([merge_one, third_input])
model = Model(inputs=[first_input, second_input, third_input], outputs=merge_two)
ada_grad = Adagrad(lr=0.1, epsilon=1e-08, decay=0.0)
model.compile(optimizer=ada_grad, loss='binary_crossentropy',
metrics=['accuracy'])
Concatenation works like this:
a b c
a b c g h i a b c g h i
d e f j k l d e f j k l
i.e rows are just joined.
2) You can say that x1 is input to first, x2 is input into second and x3 input into third.
I hope this solution solved your problem.