def get_usr_combined_features():
# FIXME(dzh) : old API integer_value(10) may has range check.
# currently we don't have user configurated check.
USR_DICT_SIZE = paddle.dataset.movielens.max_user_id() + 1
uid = layers.data(name='user_id', shape=[1], dtype='int64')
usr_emb = layers.embedding(
input=uid,
dtype='float32',
size=[USR_DICT_SIZE, 32],
param_attr='user_table',
is_sparse=IS_SPARSE)
usr_fc = layers.fc(input=usr_emb, size=32)
USR_GENDER_DICT_SIZE = 2
usr_gender_id = layers.data(name='gender_id', shape=[1], dtype='int64')
usr_gender_emb = layers.embedding(
input=usr_gender_id,
size=[USR_GENDER_DICT_SIZE, 16],
param_attr='gender_table',
is_sparse=IS_SPARSE)
usr_gender_fc = layers.fc(input=usr_gender_emb, size=16)
USR_AGE_DICT_SIZE = len(paddle.dataset.movielens.age_table)
usr_age_id = layers.data(name='age_id', shape=[1], dtype="int64")
usr_age_emb = layers.embedding(
input=usr_age_id,
size=[USR_AGE_DICT_SIZE, 16],
is_sparse=IS_SPARSE,
param_attr='age_table')
usr_age_fc = layers.fc(input=usr_age_emb, size=16)
USR_JOB_DICT_SIZE = paddle.dataset.movielens.max_job_id() + 1
usr_job_id = layers.data(name='job_id', shape=[1], dtype="int64")
usr_job_emb = layers.embedding(
input=usr_job_id,
size=[USR_JOB_DICT_SIZE, 16],
param_attr='job_table',
is_sparse=IS_SPARSE)
usr_job_fc = layers.fc(input=usr_job_emb, size=16)
concat_embed = layers.concat(
input=[usr_fc, usr_gender_fc, usr_age_fc, usr_job_fc], axis=1)
usr_combined_features = layers.fc(input=concat_embed, size=200, act="tanh")
return usr_combined_features
def get_mov_combined_features():
MOV_DICT_SIZE = paddle.dataset.movielens.max_movie_id() + 1
mov_id = layers.data(name='movie_id', shape=[1], dtype='int64')
mov_emb = layers.embedding(input=mov_id,
dtype='float32',
size=[MOV_DICT_SIZE, 32],
param_attr=smart_attr(MOV_DICT_SIZE,
name='movie_table'),
is_sparse=IS_SPARSE)
mov_fc = layers.fc(input=mov_emb, size=32, param_attr=smart_attr(32))
CATEGORY_DICT_SIZE = len(paddle.dataset.movielens.movie_categories())
# category_id = layers.data(name='category_id', shape=[1], dtype='int64')
# mov_categories_emb = layers.embedding(
# input=category_id, size=[CATEGORY_DICT_SIZE, 32], is_sparse=IS_SPARSE,
# param_attr=smart_attr(CATEGORY_DICT_SIZE))
# mov_categories_hidden = layers.sequence_pool(
# input=mov_categories_emb, pool_type="sum")
MOV_TITLE_DICT_SIZE = len(paddle.dataset.movielens.get_movie_title_dict())
mov_title_id = layers.data(name='movie_title', shape=[1], dtype='int64')
mov_title_emb = layers.embedding(
input=mov_title_id,
size=[MOV_TITLE_DICT_SIZE, 32],
is_sparse=IS_SPARSE,
param_attr=smart_attr(MOV_TITLE_DICT_SIZE))
mov_title_conv = nets.sequence_conv_pool(input=mov_title_emb,
num_filters=32,
filter_size=3,
act="tanh",
pool_type="sum")
concat_embed = layers.concat(
# input=[mov_fc, mov_categories_hidden, mov_title_conv], axis=1)
input=[mov_fc, mov_title_conv],
axis=1)
# FIXME(dzh) : need tanh operator
mov_combined_features = layers.fc(input=concat_embed,
size=200,
act="tanh",
param_attr=smart_attr(200))
return mov_combined_features
def get_usr_combined_features():
# FIXME(dzh) : old API integer_value(10) may has range check.
# currently we don't have user configurated check.
USR_DICT_SIZE = paddle.dataset.movielens.max_user_id() + 1
uid = layers.data(name='user_id', shape=[1], dtype='int64')
usr_emb = layers.embedding(input=uid,
dtype='float32',
size=[USR_DICT_SIZE, 32],
param_attr='user_table',
is_sparse=IS_SPARSE)
usr_fc = layers.fc(input=usr_emb, size=32)
USR_GENDER_DICT_SIZE = 2
usr_gender_id = layers.data(name='gender_id', shape=[1], dtype='int64')
usr_gender_emb = layers.embedding(input=usr_gender_id,
size=[USR_GENDER_DICT_SIZE, 16],
param_attr='gender_table',
is_sparse=IS_SPARSE)
usr_gender_fc = layers.fc(input=usr_gender_emb, size=16)
USR_AGE_DICT_SIZE = len(paddle.dataset.movielens.age_table)
usr_age_id = layers.data(name='age_id', shape=[1], dtype="int64")
usr_age_emb = layers.embedding(input=usr_age_id,
size=[USR_AGE_DICT_SIZE, 16],
is_sparse=IS_SPARSE,
param_attr='age_table')
usr_age_fc = layers.fc(input=usr_age_emb, size=16)
USR_JOB_DICT_SIZE = paddle.dataset.movielens.max_job_id() + 1
usr_job_id = layers.data(name='job_id', shape=[1], dtype="int64")
usr_job_emb = layers.embedding(input=usr_job_id,
size=[USR_JOB_DICT_SIZE, 16],
param_attr='job_table',
is_sparse=IS_SPARSE)
usr_job_fc = layers.fc(input=usr_job_emb, size=16)
concat_embed = layers.concat(
input=[usr_fc, usr_gender_fc, usr_age_fc, usr_job_fc], axis=1)
usr_combined_features = layers.fc(input=concat_embed, size=200, act="tanh")
return usr_combined_features
def test_word_embedding(self):
program = Program()
with program_guard(program, startup_program=Program()):
dict_size = 10000
embed_size = 32
first_word = layers.data(name='firstw', shape=[1], dtype='int64')
second_word = layers.data(name='secondw', shape=[1], dtype='int64')
third_word = layers.data(name='thirdw', shape=[1], dtype='int64')
forth_word = layers.data(name='forthw', shape=[1], dtype='int64')
next_word = layers.data(name='nextw', shape=[1], dtype='int64')
embed_first = layers.embedding(
input=first_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
embed_second = layers.embedding(
input=second_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
embed_third = layers.embedding(
input=third_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
embed_forth = layers.embedding(
input=forth_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
concat_embed = layers.concat(
input=[embed_first, embed_second, embed_third, embed_forth],
axis=1)
hidden1 = layers.fc(input=concat_embed, size=256, act='sigmoid')
predict_word = layers.fc(input=hidden1,
size=dict_size,
act='softmax')
cost = layers.cross_entropy(input=predict_word, label=next_word)
avg_cost = layers.mean(x=cost)
self.assertIsNotNone(avg_cost)
print(str(program))
def get_mov_combined_features():
MOV_DICT_SIZE = paddle.dataset.movielens.max_movie_id() + 1
mov_id = layers.data(name='movie_id', shape=[1], dtype='int64')
mov_emb = layers.embedding(
input=mov_id,
dtype='float32',
size=[MOV_DICT_SIZE, 32],
param_attr='movie_table',
is_sparse=IS_SPARSE)
mov_fc = layers.fc(input=mov_emb, size=32)
CATEGORY_DICT_SIZE = len(paddle.dataset.movielens.movie_categories())
category_id = layers.data(name='category_id', shape=[1], dtype='int64')
mov_categories_emb = layers.embedding(
input=category_id, size=[CATEGORY_DICT_SIZE, 32], is_sparse=IS_SPARSE)
mov_categories_hidden = layers.sequence_pool(
input=mov_categories_emb, pool_type="sum")
MOV_TITLE_DICT_SIZE = len(paddle.dataset.movielens.get_movie_title_dict())
mov_title_id = layers.data(name='movie_title', shape=[1], dtype='int64')
mov_title_emb = layers.embedding(
input=mov_title_id, size=[MOV_TITLE_DICT_SIZE, 32], is_sparse=IS_SPARSE)
mov_title_conv = nets.sequence_conv_pool(
input=mov_title_emb,
num_filters=32,
filter_size=3,
act="tanh",
pool_type="sum")
concat_embed = layers.concat(
input=[mov_fc, mov_categories_hidden, mov_title_conv], axis=1)
# FIXME(dzh) : need tanh operator
mov_combined_features = layers.fc(input=concat_embed, size=200, act="tanh")
return mov_combined_features
def test_word_embedding(self):
program = Program()
with program_guard(program, startup_program=Program()):
dict_size = 10000
embed_size = 32
first_word = layers.data(name='firstw', shape=[1], dtype='int64')
second_word = layers.data(name='secondw', shape=[1], dtype='int64')
third_word = layers.data(name='thirdw', shape=[1], dtype='int64')
forth_word = layers.data(name='forthw', shape=[1], dtype='int64')
next_word = layers.data(name='nextw', shape=[1], dtype='int64')
embed_first = layers.embedding(input=first_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
embed_second = layers.embedding(input=second_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
embed_third = layers.embedding(input=third_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
embed_forth = layers.embedding(input=forth_word,
size=[dict_size, embed_size],
dtype='float32',
param_attr='shared_w')
concat_embed = layers.concat(
input=[embed_first, embed_second, embed_third, embed_forth],
axis=1)
hidden1 = layers.fc(input=concat_embed, size=256, act='sigmoid')
predict_word = layers.fc(input=hidden1,
size=dict_size,
act='softmax')
cost = layers.cross_entropy(input=predict_word, label=next_word)
avg_cost = layers.mean(x=cost)
self.assertIsNotNone(avg_cost)
print(str(program))