def train(self):
self.train_dataset, \
self.test_dataset = self.data_process.generate_data(batch_size=self.batch_size,
epoch=self.epoch)
autoint = AutoInt(user_num=self.user_num,
movie_num=self.movie_num,
year_num=self.year_num,
genre_num=self.genre_num,
embedding_size=self.embedding_size,
att_embedding_size=16,
head_num=2,
att_layer_num=3,
use_res=True)
autoint_model = autoint.get_autoint_model()
autoint_model.summary()
autoint_model.compile(optimizer="adam",
loss=keras.losses.binary_crossentropy,
metrics=["accuracy"])
autoint_model.fit(self.train_dataset,
epochs=self.epoch,
steps_per_epoch=1270010 // self.batch_size + 1,
callbacks=[
get_callback(self.test_dataset, self.model_path,
self.version)
])
def train(self):
self.train_dataset, \
self.test_dataset = self.data_process.generate_data(batch_size=self.batch_size,
epoch=self.epoch)
fm = FM(user_num=self.user_num,
movie_num=self.movie_num,
year_num=self.year_num,
genre_num=self.genre_num,
embedding_size=self.embedding_size,
is_sigmoid=True)
fm_model = fm.get_fm_model()
fm_model.summary()
fm_model.compile(optimizer="adam",
loss=keras.losses.binary_crossentropy,
metrics=["accuracy"])
fm_model.fit(self.train_dataset,
epochs=self.epoch,
steps_per_epoch=1270010 // self.batch_size + 1,
callbacks=[
get_callback(self.test_dataset, self.model_path,
self.version)
])
embedding_dim=embedding_size,
embedding_name='movie_id'),
maxlen=20),
VarLenSparseFeat(SparseFeat("user_recent_click_labels",
vocabulary_size=genre_num,
embedding_dim=embedding_size,
embedding_name='current_label'),
maxlen=20),
VarLenSparseFeat(SparseFeat("user_like_genres",
vocabulary_size=genre_num,
embedding_dim=embedding_size,
embedding_name='current_label'),
maxlen=2),
]
dnn_feature_columns = feature_columns
linear_feature_columns = feature_columns
feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns)
model = WDL(linear_feature_columns, dnn_feature_columns, task='binary')
model.summary()
model.compile(optimizer="adam",
loss=keras.losses.binary_crossentropy,
metrics=["accuracy"])
model.fit(train_dataset,
epochs=epoch,
steps_per_epoch=1270010 // batch_size + 1,
callbacks=[get_callback(test_dataset, model_path, version)])
embedding_dim=embedding_size,
embedding_name='movie_id'),
maxlen=20),
VarLenSparseFeat(SparseFeat("user_recent_click_labels",
vocabulary_size=genre_num,
embedding_dim=embedding_size,
embedding_name='current_label'),
maxlen=20),
VarLenSparseFeat(SparseFeat("user_like_genres",
vocabulary_size=genre_num,
embedding_dim=embedding_size,
embedding_name='current_label'),
maxlen=2),
]
dnn_feature_columns = feature_columns
linear_feature_columns = feature_columns
feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns)
model = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary')
model.summary()
model.compile(optimizer="adam",
loss=keras.losses.binary_crossentropy,
metrics=["accuracy"])
model.fit(train_dataset,
epochs=epoch,
steps_per_epoch=1270010 // batch_size + 1,
callbacks=[get_callback(test_dataset, model_path)])