def construct_model()

in example_zoo/tensorflow/models/ncf_main/official/recommendation/neumf_model.py [0:0]

• 52 lines of code
• 7 McCabe index (conditional complexity)

def construct_model(users, items, params):
  # type: (tf.Tensor, tf.Tensor, dict) -> tf.keras.Model
  """Initialize NeuMF model.

  Args:
    users: Tensor of user ids.
    items: Tensor of item ids.
    params: Dict of hyperparameters.
  Raises:
    ValueError: if the first model layer is not even.
  Returns:
    model:  a keras Model for computing the logits
  """
  num_users = params["num_users"]
  num_items = params["num_items"]

  model_layers = params["model_layers"]

  mf_regularization = params["mf_regularization"]
  mlp_reg_layers = params["mlp_reg_layers"]

  mf_dim = params["mf_dim"]

  mlperf_helper.ncf_print(key=mlperf_helper.TAGS.MODEL_HP_MF_DIM, value=mf_dim)
  mlperf_helper.ncf_print(key=mlperf_helper.TAGS.MODEL_HP_MLP_LAYER_SIZES,
                          value=model_layers)

  if model_layers[0] % 2 != 0:
    raise ValueError("The first layer size should be multiple of 2!")

  # Input variables
  user_input = tf.keras.layers.Input(tensor=users, name="user_input")
  item_input = tf.keras.layers.Input(tensor=items, name="item_input")

  # Initializer for embedding layers
  embedding_initializer = "glorot_uniform"

  # It turns out to be significantly more effecient to store the MF and MLP
  # embedding portions in the same table, and then slice as needed.
  mf_slice_fn = lambda x: x[:, :mf_dim]
  mlp_slice_fn = lambda x: x[:, mf_dim:]
  embedding_user = tf.keras.layers.Embedding(
      num_users, mf_dim + model_layers[0] // 2,
      embeddings_initializer=embedding_initializer,
      embeddings_regularizer=tf.keras.regularizers.l2(mf_regularization),
      input_length=1, name="embedding_user")(user_input)

  embedding_item = tf.keras.layers.Embedding(
      num_items, mf_dim + model_layers[0] // 2,
      embeddings_initializer=embedding_initializer,
      embeddings_regularizer=tf.keras.regularizers.l2(mf_regularization),
      input_length=1, name="embedding_item")(item_input)

  # GMF part
  mf_user_latent = tf.keras.layers.Lambda(
      mf_slice_fn, name="embedding_user_mf")(embedding_user)
  mf_item_latent = tf.keras.layers.Lambda(
      mf_slice_fn, name="embedding_item_mf")(embedding_item)

  # MLP part
  mlp_user_latent = tf.keras.layers.Lambda(
      mlp_slice_fn, name="embedding_user_mlp")(embedding_user)
  mlp_item_latent = tf.keras.layers.Lambda(
      mlp_slice_fn, name="embedding_item_mlp")(embedding_item)

  # Element-wise multiply
  mf_vector = tf.keras.layers.multiply([mf_user_latent, mf_item_latent])

  # Concatenation of two latent features
  mlp_vector = tf.keras.layers.concatenate([mlp_user_latent, mlp_item_latent])

  num_layer = len(model_layers)  # Number of layers in the MLP
  for layer in xrange(1, num_layer):
    model_layer = tf.keras.layers.Dense(
        model_layers[layer],
        kernel_regularizer=tf.keras.regularizers.l2(mlp_reg_layers[layer]),
        activation="relu")
    mlp_vector = model_layer(mlp_vector)

  # Concatenate GMF and MLP parts
  predict_vector = tf.keras.layers.concatenate([mf_vector, mlp_vector])

  # Final prediction layer
  logits = tf.keras.layers.Dense(
      1, activation=None, kernel_initializer="lecun_uniform",
      name=movielens.RATING_COLUMN)(predict_vector)

  # Print model topology.
  model = tf.keras.models.Model([user_input, item_input], logits)
  model.summary()
  sys.stdout.flush()

  return model