Squared X Tensorflow Model

Question

I'm learning Tensorflow 2 and cannot accomplish a very basic task, I want to train my model so it would calculate the squared value of a given number (y=x*x)

Here is my code:

    # random vector of inputs
    x = tf.random.uniform((1000,), minval=-100, maxval=100, dtype='int32')
    # labels (squared input)
    y = tf.convert_to_tensor(list(n * n for n in x))

    model = keras.Sequential([
        keras.layers.Dense(1),
    ])

    model.compile(loss=keras.losses.binary_crossentropy, optimizer='adam')
    model.fit(x, y, epochs=5, batch_size=50)

    print(model.predict([2]))

Why it doesn't work?

Answer 1

So my error was in that I expected my model would return the squared value instead of the slope (y = x * slop + bias), here is the fixed version (that works):

    # random vector of inputs
    x = tf.random.uniform((1000,), minval=-100, maxval=100, dtype='int32')
    # labels (slops)
    y = tf.convert_to_tensor(list(n for n in x))

    model = keras.Sequential([
        keras.layers.Dense(1)
    ])

    model.compile(optimizer='adam', loss='mean_absolute_error')

    model.fit(x, y, epochs=10, batch_size=50)

    print(2 * int(model.predict([2])))

>4