shall i use a sequential model or Functional API to model a neural network for two input 2D matrix

Question

Good morning,

i tried to use a sequential model to create my neural network which have a multiple input (concatenated). But i want to know if shall i use The Keras functional API to CREATE my model.

in1= loadtxt('in1.csv', delimiter=',')#2D matrix
in2= loadtxt('in2.csv', delimiter=',')#2D matrix
y= loadtxt('y.csv', delimiter=',') #2D matrix (output labels)
X_train=np.hstack((in1,in2))
y_train=y
model = Sequential()
model.add(Dense(nbinneuron, input_dim=2*nx,activation='tanh',kernel_initializer='normal'))
model.add(Dropout(0.5))
#output layer
model.add(Dense(2, activation='tanh'))
opt =Adalta(lr=0.01)
model.compile(loss='mean_squared_error', optimizer=opt, metrics=['mse'])
# fit the keras model on the dataset
history=model.fit(X_train, y_train,validation_data=(X_test, y_test), epochs=500,verbose=0)
...

thanks an advance

Answer 1

A Sequential Model can only have one input and one output. To build a model with multiple inputs (and/or multiple outputs), you need to use the Functional API.