def make_keras_model()

in tcav/tcav_examples/discrete/kdd99_model.py [0:0]

• 34 lines of code
• 5 McCabe index (conditional complexity)

def make_keras_model(categorical_map):
  """Simple feedforward model.

  Uses embedding representation for categorical variables.
  """
  n_features = 41
  n_labels = 23
  # Make all placeholders
  inputs = []
  models = []

  input_layer = tf.keras.layers.Input(shape=(n_features,), name='input')
  inputs.append(input_layer)

  # Splits the input vector into multiple variables
  deconcat = tf.split(input_layer, [1 for i in range(n_features)], 1)

  for index in range(n_features):
    # For categorical variables, we create embedding layers
    if index in categorical_map.keys():
      vocab_size = categorical_map[index]
      inpt = deconcat[index]
      inputs.append(inpt)
      embed = tf.keras.layers.Embedding(vocab_size, 200, \
                                        trainable=True,
                                        embeddings_initializer=tf.compat.v1.initializers.random_normal())(inpt)

      embed_reshaped = tf.keras.layers.Reshape(target_shape=(200,))(embed)
      models.append(embed_reshaped)
    else:
      # Else, create a simple input for numerical features
      inpt = deconcat[index]
      inputs.append(inpt)
      models.append(inpt)

  # Concatenate them into a single vector
  merge_models = tf.keras.layers.concatenate(models)

  # Plug them into the DNN
  net = tf.keras.layers.Dense(1000)(merge_models)
  net = tf.keras.layers.BatchNormalization()(net)
  net = tf.keras.layers.Dense(256)(net)
  net = tf.keras.layers.BatchNormalization()(net)

  pred = tf.keras.layers.Dense(n_labels, activation='sigmoid')(net)
  model_full = tf.keras.models.Model(inputs=input_layer, \
                                     outputs=pred)
  model_full.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), \
                     metrics=['accuracy'],
                     optimizer='adam')
  return model_full