Variables cannot be used in array

Question

I'm trying to create a neural network to add and subtract integers. The code is as below:

model_add = Sequential(
        [
            Dense(10, activation='relu'),
            Dense(1, activation ='relu')
            ]
        )

model_subtract = Sequential(
        [
            Dense(10, activation='relu'),
            Dense(1, activation ='relu')
            ]
        )

model_add.compile(loss = 'mse', optimizer='adam')
batch_size = 32
epochs = 100
model_add.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, verbose = 0)


model_subtract.compile(loss = 'mse', optimizer='adam')
batch_size = 32
epochs = 100
model_add.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, verbose = 0)

print("enter first num:")
x = input()

print("Enter operation:")
op= input()

print("enter second num:")
y = input()

X = int(x)
Y = int(y)

if op == "+":
    predicted_sum = model_add.predict([X, Y])
    print(predicted_sum)
elif op =="-":
    predicted_sum = model_subtract.predict([X, Y])
    print(predicted_sum)

On input 1+2, this gives rise to an error:

raise ValueError(f"Unrecognized data type: x={x} (of type {type(x)})")
ValueError: Unrecognized data type: x=[1, 2] (of type <class 'list'>)

Can someone explain why this happens and how to fix it?

Answer 1

The problem was solved by replacing [X, Y] with np.array([[X, Y]])