remove print statements and old code

    learning_rate: float

      Learning rate for the model.

    """

    # TODO: Turning off queue for now. Safe to re-activate?

    self.complex_num_atoms = complex_num_atoms

    self.frag1_num_atoms = frag1_num_atoms

    self.frag2_num_atoms = frag2_num_atoms

      regularizer = None

    prev_layer = concat

    # dropout_switch = Input(shape=tuple())

    prev_size = concat.shape[0]

    next_activation = None

    # Add the dense layers

    for size, weight_stddev, bias_const, dropout, activation_fn in zip(

      layer = prev_layer

      if next_activation is not None:

        layer = Activation(next_activation)(layer)

      # layer = Dense(100)(layer)

      layer = Dense(

          size,

          kernel_initializer=tf.keras.initializers.TruncatedNormal(

        bias_initializer=tf.constant_initializer(

            value=bias_init_consts[-1]))(prev_layer))

    loss: Union[dc.models.losses.Loss, LossFn]

    # prev_layer = Dense(100)(prev_layer)

    # output = Dense(1)(prev_layer)

    # print("output")

    # print(output)

    # loss = dc.models.losses.L2Loss()

    model = tf.keras.Model(

        inputs=[

            frag2_nbrs_z, frag2_z, complex_X, complex_nbrs, complex_nbrs_z,

            complex_z

        ],

        # outputs=score)

        outputs=output)

    super(AtomicConvModel, self).__init__(

        model, L2Loss(), batch_size=batch_size, **kwargs)

  frag1_z = np.random.randint(10, size=(N_atoms))

  frag2_coords = np.random.rand(N_atoms, 3)

  frag2_nbr_list = {0: [], 1: [], 2: [], 3: [], 4: []}

  # frag2_z = np.random.rand(N_atoms, 3)

  frag2_z = np.random.randint(10, size=(N_atoms))

  system_coords = np.random.rand(2 * N_atoms, 3)

  system_nbr_list = {

  labels = np.random.rand(batch_size)

  train = NumpyDataset(features, labels)

  atomic_convnet.fit(train, nb_epoch=150)

  print("labels")

  print(labels)

  print("atomic_convnet.predict(train)")

  print(atomic_convnet.predict(train))

  assert np.allclose(labels, atomic_convnet.predict(train), atol=0.01)