train2modelmmoe.py

import tensorflow as tf
from tensorflow.python.keras.layers import Input, Dense
from deepctr.inputs import input_from_feature_columns, get_linear_logit,build_input_features,combined_dnn_input
from deepctr.layers.core import PredictionLayer, DNN
from deepctr.layers.interaction import FM
from deepctr.layers.utils import concat_fun
from tensorflow.python.keras.initializers import VarianceScaling

from mymmoe import MMoE

def DeepFMmmoe(linear_feature_columns, dnn_feature_columns, embedding_size=8, use_fm=True, dnn_hidden_units=(128, 128),
           l2_reg_linear=0.00001, l2_reg_embedding=0.00001, l2_reg_dnn=0, init_std=0.0001, seed=1024, dnn_dropout=0,
           dnn_activation='relu', dnn_use_bn=False, task='binary', task_net_size=(128, )):
    """Instantiates the DeepFM Network architecture.

    :param linear_feature_columns: An iterable containing all the features used by linear part of the model.
    :param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
    :param embedding_size: positive integer,sparse feature embedding_size
    :param use_fm: bool,use FM part or not
    :param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of DNN
    :param l2_reg_linear: float. L2 regularizer strength applied to linear part
    :param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
    :param l2_reg_dnn: float. L2 regularizer strength applied to DNN
    :param init_std: float,to use as the initialize std of embedding vector
    :param seed: integer ,to use as random seed.
    :param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
    :param dnn_activation: Activation function to use in DNN
    :param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in DNN
    :param task: str, ``"binary"`` for  binary logloss or  ``"regression"`` for regression loss
    :return: A Keras model instance.
    """

    features = build_input_features(linear_feature_columns + dnn_feature_columns)

    inputs_list = list(features.values())

    sparse_embedding_list, dense_value_list = input_from_feature_columns(features,dnn_feature_columns,
                                                                              embedding_size,
                                                                              l2_reg_embedding,init_std,
                                                                              seed)

    # linear_logit = get_linear_logit(features, linear_feature_columns, l2_reg=l2_reg_linear, init_std=init_std,
    #                                 seed=seed, prefix='linear')
    #
    # fm_input = concat_fun(sparse_embedding_list, axis=1)
    # fm_logit = FM()(fm_input)

    dnn_input = combined_dnn_input(sparse_embedding_list,dense_value_list)
    #dnn_logit = tf.keras.layers.Dense(
    #    1, use_bias=False, activation=None)(dnn_out)
    mmoe_layers = MMoE(units=32, num_experts=4, num_tasks=2)(dnn_input)

    output_layers = []
    target=['finish', 'like']
    # Build tower layer from MMoE layer
    for index, task_layer in enumerate(mmoe_layers):
        tower_layer = Dense(
            units=128,
            activation='relu',
            kernel_initializer=VarianceScaling())(task_layer)
        output_layer = Dense(
            units=1,
            name=target[index],
            activation='sigmoid',
            kernel_initializer=VarianceScaling())(tower_layer)
        output_layers.append(output_layer)


    # finish_logit = tf.keras.layers.add(
    #     [linear_logit, output_layers[0], fm_logit])
    # like_logit = tf.keras.layers.add(
    #     [linear_logit, output_layers[1], fm_logit])
    #
    # output_finish = PredictionLayer(task, name='finish_')(finish_logit)
    # output_like = PredictionLayer(task, name='like_')(like_logit)
    model = tf.keras.models.Model(inputs=inputs_list, outputs=output_layers)#[output_finish, output_like])
    return model

    # if len(dnn_hidden_units) == 0 and use_fm == False:  # only linear
    #     final_logit = linear_logit
    # elif len(dnn_hidden_units) == 0 and use_fm == True:  # linear + FM
    #     final_logit = tf.keras.layers.add([linear_logit, fm_logit])
    # elif len(dnn_hidden_units) > 0 and use_fm == False:  # linear +　Deep
    #     final_logit = tf.keras.layers.add([linear_logit, dnn_logit])
    # elif len(dnn_hidden_units) > 0 and use_fm == True:  # linear + FM + Deep
    #     final_logit = tf.keras.layers.add([linear_logit, fm_logit, dnn_logit])
    # else:
    #     raise NotImplementedError

    # output = PredictionLayer(task)(final_logit)
    # model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
    # return model