如何用两个不同大小的输入馈送神经网络？

Question

I want to feed a Neural Network with two inputs. The first dataset (elements) will have a fixed shape of (20, 1), which means that it will be the same for both the training and the test phase (it will never change). It consists of values between 1-100. The second input dataset will consist of 20 binary features (columns) and N data (shape: (N,20)), and each row of this dataset will indicate which rows of the elements dataset were combined. The output will have a shape of (N,1), and it will be the result of the corresponding elements' combinations, after applying a specific function to them.

I know how to build a model with multiple inputs when we have the same number of rows in both datasets, and my approach so far is the following:

# define two sets of inputs
inputA = Input(shape=(1,))
inputB = Input(shape=(elements.shape[0],))

# the first branch operates on the first input
x = Dense(100, activation="relu")(inputA)
x = Dense(50, activation="relu")(x)
x = Model(inputs=inputA, outputs=x)

# the second branch opreates on the second input
y = Dense(100, activation="relu")(inputB)
y = Dense(100, activation="relu")(y)
y = Dense(50, activation="relu")(y)
y = Model(inputs=inputB, outputs=y)

# combine the output of the two branches
combined = concatenate([x.output, y.output])

# apply a FC layer and then a regression prediction on the
# combined outputs
z = Dense(50, activation="relu")(combined)
z = Dense(1, activation="linear")(z)

# our model will accept the inputs of the two branches and
# then output a single value
model = Model(inputs=[x.input, y.input], outputs=z)

model.compile(loss="mean_squared_error", optimizer=Adam())

# train the model
print("[INFO] training model...")
model.fit([elements, X_train], y_train, epochs=200, verbose=1)

However, since the "elements" dataset is fixed, the rows of the 1st input are different from the rows of the 2nd input. The following error occurs.

ValueError: All input arrays (x) should have the same number of samples. Got array shapes: [(20, 1), (33, 20)]

Do you know how could I overcome this problem?

Answer 1

The short answer is that the batch_size of all your inputs (and outputs) must be the same. But nothing prevents you from repeating your (20, 1) dataset for each entry in the batch size, thus resulting in a shape of (N, 20, 1).

Please note that has the other people on this thread noted, this approach seems like the wrong thing to do.