def model_fn(labels, features, mode, params):
tf.set_random_seed(2019)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
single_cate_feats = cate_feats[:, 0:params.cate_field_size]
multi_cate_feats = cate_feats[:, params.cate_field_size:params.cate_field_size + params.multi_feats_size]
attention_cate_feats = cate_feats[:, params.cate_field_size + params.multi_feats_size:]
# init_embedding
feats_emb = my_layer.emb_init(name='feats_emb', feat_num=params.cate_feats_size, embedding_size=params.embedding_size)
# single_category -> embedding
single_cate_emb = tf.nn.embedding_lookup(feats_emb, ids=single_cate_feats)
single_cate_emb = tf.reshape(single_cate_emb, shape=[-1, params.cate_field_size * params.embedding_size])
# attention
attention_emb = attention_alg(params, feats_emb, multi_cate_feats, single_cate_feats, attention_cate_feats)
# multi_category -> embedding
multi_cate_emb = my_layer.multi_cate_emb(params.multi_feats_range, feats_emb, multi_cate_feats)
# deep input dense
if len(params.multi_feats_range) > 0:
dense = tf.concat([cont_feats, vector_feats, single_cate_emb, multi_cate_emb, attention_emb], axis=1, name='dense_vector')
else:
dense = tf.concat([cont_feats, vector_feats, single_cate_emb, attention_emb], axis=1, name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
dense = tf.layers.dense(inputs=dense, units=params.hidden_units[i], activation=tf.nn.relu)
out = tf.layers.dense(inputs=dense, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(features, labels, mode, params):
tf.set_random_seed(2019)
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
feats_emb = my_layer.emb_init(name='feats_emb',
feat_num=params.cate_feats_size,
embedding_size=params.embedding_size)
# category -> Embedding
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=cate_feats)
cate_emb = tf.reshape(
cate_emb, shape=[-1, params.cate_field_size * params.embedding_size])
# deep input dense
dense = tf.concat([vector_feats, cate_emb], axis=1, name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
dense = tf.layers.dense(inputs=dense,
units=params.hidden_units[i],
activation=tf.nn.relu)
out = tf.layers.dense(inputs=dense, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2020)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
cont_feats_index = tf.Variable(
[[i for i in range(params.cont_field_count)]],
trainable=False,
dtype=tf.int64,
name="cont_feats_index")
cont_feats_index = tf.add(cont_feats_index, params.cate_emb_space_size)
feats_size = params.cont_field_count + params.cate_emb_space_size
feats_emb = my_layer.emb_init(name='feats_emb',
feat_num=feats_size,
embedding_size=params.embedding_size)
cont_emb = tf.nn.embedding_lookup(
feats_emb, ids=cont_feats_index) # None * F * embedding_size
cont_value = tf.reshape(cont_feats, shape=[-1, params.cont_field_count, 1])
embeddings = tf.multiply(cont_emb, cont_value)
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=cate_feats)
embeddings = tf.concat([embeddings, cate_emb], axis=1)
if params.multi_feats_type == 'dense':
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(
feats_emb,
ids=features[name_topN[0]]) # None, topN, embedding_size
dense_embedding = tf.reduce_sum(dense_embedding, axis=1) # None, 1
dense_embedding = tf.reshape(dense_embedding,
shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, dense_embedding], axis=1)
else: # sparse
for name_topN in params.multi_cate_field_list:
sparse_embedding = tf.nn.embedding_lookup_sparse(
feats_emb,
sp_ids=features[name_topN[0]],
sp_weights=None,
combiner='sum') # None * embedding_size
sparse_embedding = tf.reshape(sparse_embedding,
shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, sparse_embedding], axis=1)
deep_emb = tf.reshape(
embeddings,
shape=[-1, params.total_field_count * params.embedding_size])
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
deep_emb = tf.layers.dense(inputs=deep_emb,
units=params.hidden_units[i],
activation=tf.nn.relu)
out = tf.layers.dense(inputs=deep_emb, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2020)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
cont_feats_index = tf.Variable([[i for i in range(params.cont_field_count)]], trainable=False, dtype=tf.int64, name="cont_feats_index")
cont_feats_index = tf.add(cont_feats_index, params.cate_emb_space_size)
feats_size = params.cont_field_count + params.cate_emb_space_size
feats_emb = my_layer.emb_init(name='feats_emb', feat_num=feats_size, embedding_size=params.embedding_size)
# cont_feats
cont_emb = tf.nn.embedding_lookup(feats_emb, ids=cont_feats_index) # None * F * embedding_size
cont_value = tf.reshape(cont_feats, shape=[-1, params.cont_field_count, 1])
embeddings = tf.multiply(cont_emb, cont_value)
# cate_feats
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=cate_feats)
embeddings = tf.concat([embeddings, cate_emb], axis=1)
# multi_cate_feats
for name_topN in params.multi_cate_field_list:
multi_cate_emb = tf.nn.embedding_lookup(feats_emb, ids=features[name_topN[0]]) # None, topN, embedding_size
multi_cate_emb = tf.reduce_sum(multi_cate_emb, axis=1) # None, embedding_size
multi_cate_emb = tf.reshape(multi_cate_emb, shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, multi_cate_emb], axis=1)
# target-attention 1vN (e.g. item_cat1 & user_click_cat1)
for k_v in params.target_att_1vN_list:
item_feat = tf.split(cate_feats, params.cate_field_count, axis=1)[k_v[1]]
user_feat = features[k_v[0]]
nonzero_len = tf.count_nonzero(user_feat, axis=1)
item_emb = tf.nn.embedding_lookup(feats_emb, ids=item_feat) # [B, 1, H]
item_emb = tf.reshape(item_emb, shape=[-1, params.embedding_size]) # [B, H]
user_emb = tf.nn.embedding_lookup(feats_emb, ids=user_feat) # [B, T, H])
att_1vN_emb = my_layer.attention(item_emb, user_emb, nonzero_len) # [B, 1, H]
embeddings = tf.concat([embeddings, att_1vN_emb], axis=1)
# target-attention NvN (e.g. item_tags & user_click_tags)
for k_v in params.target_att_NvN_list:
item_feat = features[k_v[1]]
user_feat = features[k_v[0]]
nonzero_len = tf.count_nonzero(user_feat, axis=1)
item_emb = tf.nn.embedding_lookup(feats_emb, ids=item_feat) # [B, N, H]
user_emb = tf.nn.embedding_lookup(feats_emb, ids=user_feat) # [B, T, H])
att_NvN_emb = my_layer.attention_multi(item_emb, user_emb, nonzero_len) # [B, 1, H]
embeddings = tf.concat([embeddings, att_NvN_emb], axis=1)
# deep
embeddings = tf.layers.flatten(embeddings)
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
embeddings = tf.layers.dense(inputs=embeddings, units=params.hidden_units[i], activation=tf.nn.relu)
out = tf.layers.dense(inputs=embeddings, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2019)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
single_cate_feats = cate_feats[:, 0:params.cate_field_size]
# multi_cate_feats = cate_feats[:, params.cate_field_size:]
feats_emb = my_layer.emb_init(name='feats_emb',
feat_num=params.cate_feats_size,
embedding_size=params.embedding_size)
# single_category -> embedding
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=single_cate_feats)
cate_emb = tf.reshape(
cate_emb, shape=[-1, params.cate_field_size * params.embedding_size])
# aid -> attention
aid = vector_feats[:, -112:-96]
user_click_aids = vector_feats[:, -96:]
user_click_aids = tf.reshape(user_click_aids, shape=[-1, 6, 16])
user_click_aids_len = tf.constant(
6, shape=[user_click_aids.get_shape().as_list()[0]])
attention_emb = attention(aid, user_click_aids, user_click_aids_len)
attention_emb = tf.reshape(attention_emb, shape=[-1, 16])
# deep input dense
dense = tf.concat([cont_feats, vector_feats, cate_emb, attention_emb],
axis=1,
name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
dense = tf.layers.dense(inputs=dense,
units=params.hidden_units[i],
activation=tf.nn.relu)
out = tf.layers.dense(inputs=dense, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2020)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
cont_feats_index = tf.Variable([[i for i in range(params.cont_field_count)]], trainable=False, dtype=tf.int64, name="cont_feats_index")
cont_feats_index = tf.add(cont_feats_index, params.cate_emb_space_size)
feats_size = params.cont_field_count + params.cate_emb_space_size
weights = dict()
weights["feats_emb"] = tf.get_variable(name='feats_emb', shape=[feats_size, params.embedding_size], initializer=tf.glorot_normal_initializer())
weights["feats_bias"] = tf.get_variable(name='feats_bias', shape=[feats_size, 1], initializer=tf.glorot_normal_initializer())
with tf.name_scope('fm_part'):
# FM_first_order [?, total_field_count]
first_cont_emb = tf.nn.embedding_lookup(weights["feats_bias"], ids=cont_feats_index) # [None, F, 1]
first_cont_emb = tf.reshape(first_cont_emb, shape=[-1, params.cont_field_count])
first_order = tf.multiply(first_cont_emb, cont_feats)
first_cate_emb = tf.nn.embedding_lookup(weights["feats_bias"], ids=cate_feats)
first_cate_emb = tf.reshape(first_cate_emb, shape=[-1, params.cate_field_count])
first_order = tf.concat([first_order, first_cate_emb], axis=1)
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(weights["feats_bias"], ids=features[name_topN[0]]) # [None, topN, 1]
dense_embedding = tf.reduce_sum(dense_embedding, axis=1) # [None, 1]
first_order = tf.concat([first_order, dense_embedding], axis=1)
# FM_second_order [?, embedding_size]
second_cont_emb = tf.nn.embedding_lookup(weights["feats_emb"], ids=cont_feats_index) # [None, F, embedding_size]
second_cont_value = tf.reshape(cont_feats, shape=[-1, params.cont_field_count, 1])
embeddings = tf.multiply(second_cont_emb, second_cont_value)
second_cate_emb = tf.nn.embedding_lookup(weights["feats_emb"], ids=cate_feats)
embeddings = tf.concat([embeddings, second_cate_emb], axis=1) # [None, F, embedding_size]
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(weights["feats_emb"], ids=features[name_topN[0]]) # [None, topN, embedding_size]
dense_embedding = tf.reduce_sum(dense_embedding, axis=1) # [None, embedding_size]
dense_embedding = tf.reshape(dense_embedding, shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, dense_embedding], axis=1)
# target-attention 1vN (e.g. item_cat1 & user_click_cat1)
for k_v in params.target_att_1vN_list:
item_feat = tf.split(cate_feats, params.cate_field_count, axis=1)[k_v[1]]
user_feat = features[k_v[0]]
nonzero_len = tf.count_nonzero(user_feat, axis=1)
item_emb = tf.nn.embedding_lookup(weights["feats_emb"], ids=item_feat) # [B, 1, H]
item_emb = tf.reshape(item_emb, shape=[-1, params.embedding_size]) # [B, H]
user_emb = tf.nn.embedding_lookup(weights["feats_emb"], ids=user_feat) # [B, T, H])
att_1vN_emb = my_layer.attention(item_emb, user_emb, nonzero_len) # [B, 1, H]
embeddings = tf.concat([embeddings, att_1vN_emb], axis=1)
# target-attention NvN (e.g. item_tags & user_click_tags)
for k_v in params.target_att_NvN_list:
item_feat = features[k_v[1]]
user_feat = features[k_v[0]]
nonzero_len = tf.count_nonzero(user_feat, axis=1)
item_emb = tf.nn.embedding_lookup(weights["feats_emb"], ids=item_feat) # [B, N, H]
user_emb = tf.nn.embedding_lookup(weights["feats_emb"], ids=user_feat) # [B, T, H])
att_NvN_emb = my_layer.attention_multi(item_emb, user_emb, nonzero_len) # [B, 1, H]
embeddings = tf.concat([embeddings, att_NvN_emb], axis=1)
sum_emb = tf.reduce_sum(embeddings, 1)
sum_square_emb = tf.square(sum_emb)
square_emb = tf.square(embeddings)
square_sum_emb = tf.reduce_sum(square_emb, 1)
second_order = 0.5 * tf.subtract(sum_square_emb, square_sum_emb)
# FM_res [?, total_field_count + embedding_size]
fm_res = tf.concat([first_order, second_order], axis=1)
with tf.name_scope('deep_part'):
deep_res = tf.layers.flatten(embeddings)
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
deep_res = tf.layers.dense(inputs=deep_res, units=params.hidden_units[i], activation=tf.nn.relu)
with tf.name_scope('deep_fm'):
input_size = params.total_field_count + params.embedding_size + params.hidden_units[-1] # FM_res->total_field_count+embedding_size, Deep_res->hidden_units[-1]
weights["concat_emb"] = tf.get_variable(name='concat_emb', shape=[input_size, 1], initializer=tf.glorot_normal_initializer())
weights["concat_bias"] = tf.get_variable(name='concat_bias', shape=[1], initializer=tf.constant_initializer(0.01))
feats_input = tf.concat([fm_res, deep_res], axis=1)
out = tf.add(tf.matmul(feats_input, weights["concat_emb"]), weights["concat_bias"])
y = tf.nn.sigmoid(out)
model_estimator_spec = op.model_optimizer(params, mode, labels, y)
return model_estimator_spec
def model_fn(features, labels, mode, params):
use_deep = True
use_fm = True
tf.set_random_seed(2019)
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
index_max_size = params.cont_field_size + params.cate_feats_size
fm_first_order_emb = my_layer.emb_init(name='fm_first_order_emb', feat_num=index_max_size, embedding_size=1)
feats_emb = my_layer.emb_init(name='feats_emb', feat_num=index_max_size, embedding_size=params.embedding_size)
with tf.name_scope('fm_part'):
input_field_size = params.cont_field_size + params.cate_field_size + params.multi_field_size
# FM_first_order [?, input_field_size]
# cate
first_cate_emb = tf.nn.embedding_lookup(fm_first_order_emb, ids=cate_feats)
first_cate_emb = tf.reshape(first_cate_emb, shape=[-1, params.cate_field_size])
first_order = tf.nn.dropout(first_cate_emb, params.dropout_keep_fm[0])
# FM_second_order [?, embedding_size]
# cate
second_order_emb = tf.nn.embedding_lookup(feats_emb, ids=cate_feats)
sum_emb = tf.reduce_sum(second_order_emb, 1)
sum_square_emb = tf.square(sum_emb)
square_emb = tf.square(second_order_emb)
square_sum_emb = tf.reduce_sum(square_emb, 1)
second_order = 0.5 * tf.subtract(sum_square_emb, square_sum_emb)
second_order = tf.nn.dropout(second_order, params.dropout_keep_fm[1])
print("fm_second_order:", second_order)
# FM_res [?, self.input_field_size + embedding_size]
fm_res = tf.concat([first_order, second_order], axis=1)
with tf.name_scope('deep_part'):
# category -> Embedding
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=cate_feats)
cate_emb = tf.reshape(cate_emb, shape=[-1, params.cate_field_size * params.embedding_size])
# dense input
deep_res = tf.concat([vector_feats, cate_emb], axis=1, name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
deep_res = tf.layers.dense(inputs=deep_res, units=params.hidden_units[i], activation=tf.nn.relu)
with tf.name_scope('deep_fm'):
if use_fm and use_deep:
feats_input = tf.concat([fm_res, deep_res], axis=1)
feats_input_size = input_field_size + params.embedding_size + params.hidden_units[-1]
elif use_fm:
feats_input = fm_res
feats_input_size = input_field_size + params.embedding_size
elif use_deep:
feats_input = deep_res
feats_input_size = params.hidden_units[-1]
glorot = np.sqrt(2.0 / (feats_input_size + 1))
deep_fm_weight = tf.Variable(
np.random.normal(loc=0, scale=glorot, size=(feats_input_size, 1)), dtype=np.float32)
deep_fm_bias = tf.Variable(tf.random_normal([1]))
out = tf.add(tf.matmul(feats_input, deep_fm_weight), deep_fm_bias)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
use_deep = True
use_fm = True
tf.set_random_seed(2019)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
single_cate_feats = cate_feats[:, 0:params.cate_field_size]
multi_cate_feats = cate_feats[:, params.cate_field_size:]
cont_feats_index = tf.Variable([[i for i in range(params.cont_field_size)]], trainable=False, dtype=tf.int64, name="cont_feats_index")
index_max_size = params.cont_field_size + params.cate_feats_size
fm_first_order_emb = my_layer.emb_init(name='fm_first_order_emb', feat_num=index_max_size, embedding_size=1)
feats_emb = my_layer.emb_init(name='feats_emb', feat_num=index_max_size, embedding_size=params.embedding_size)
with tf.name_scope('fm_part'):
input_field_size = params.cont_field_size + params.cate_field_size + len(params.multi_feats_range)
cont_index_add = tf.add(cont_feats_index, params.cate_feats_size)
# FM_first_order [?, input_field_size]
# cont
first_cont_emb = tf.nn.embedding_lookup(fm_first_order_emb, ids=cont_index_add)
first_cont_emb = tf.reshape(first_cont_emb, shape=[-1, params.cont_field_size])
first_cont_mul = tf.multiply(first_cont_emb, cont_feats)
# single_cate
first_single_cate_emb = tf.nn.embedding_lookup(fm_first_order_emb, ids=single_cate_feats)
first_single_cate_emb = tf.reshape(first_single_cate_emb, shape=[-1, params.cate_field_size])
# multi_cate
first_multi_cate_emb = my_layer.multi_cate_emb(params.multi_feats_range, fm_first_order_emb, multi_cate_feats)
# concat cont & single_cate & multi_cate
first_order_emb = tf.concat([first_cont_mul, first_single_cate_emb, first_multi_cate_emb], axis=1)
first_order = tf.nn.dropout(first_order_emb, params.dropout_keep_fm[0])
# FM_second_order [?, embedding_size]
# cont
second_cont_emb = tf.nn.embedding_lookup(feats_emb, ids=cont_index_add)
second_cont_value = tf.reshape(cont_feats, shape=[-1, params.cont_field_size, 1])
second_cont_emb = tf.multiply(second_cont_emb, second_cont_value)
# single_cate
second_single_cate_emb = tf.nn.embedding_lookup(feats_emb, ids=single_cate_feats)
# multi_cate
second_multi_cate_emb = my_layer.multi_cate_emb(params.multi_feats_range, feats_emb, multi_cate_feats)
second_multi_cate_emb = tf.reshape(second_multi_cate_emb,
shape=[-1, len(params.multi_feats_range), params.embedding_size])
# concat cont & single_cate & multi_cate
second_order_emb = tf.concat([second_cont_emb, second_single_cate_emb, second_multi_cate_emb], axis=1)
sum_emb = tf.reduce_sum(second_order_emb, 1)
sum_square_emb = tf.square(sum_emb)
square_emb = tf.square(second_order_emb)
square_sum_emb = tf.reduce_sum(square_emb, 1)
second_order = 0.5 * tf.subtract(sum_square_emb, square_sum_emb)
second_order = tf.nn.dropout(second_order, params.dropout_keep_fm[1])
# FM_res [?, self.input_field_size + embedding_size]
fm_res = tf.concat([first_order, second_order], axis=1)
with tf.name_scope('deep_part'):
# single_cate
single_cate_emb = tf.nn.embedding_lookup(feats_emb, ids=single_cate_feats)
single_cate_emb = tf.reshape(single_cate_emb, shape=[-1, params.cate_field_size * params.embedding_size])
# multi_cate
multi_cate_emb = my_layer.multi_cate_emb(params.multi_feats_range, feats_emb, multi_cate_feats)
deep_res = tf.concat([cont_feats, vector_feats, single_cate_emb, multi_cate_emb], axis=1, name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
deep_res = tf.layers.dense(inputs=deep_res, units=params.hidden_units[i], activation=tf.nn.relu)
with tf.name_scope('deep_fm'):
if use_fm and use_deep:
feats_input = tf.concat([fm_res, deep_res], axis=1)
feats_input_size = input_field_size + params.embedding_size + params.hidden_units[-1]
elif use_fm:
feats_input = fm_res
feats_input_size = input_field_size + params.embedding_size
elif use_deep:
feats_input = deep_res
feats_input_size = params.hidden_units[-1]
glorot = np.sqrt(2.0 / (feats_input_size + 1))
deep_fm_weight = tf.Variable(
np.random.normal(loc=0, scale=glorot, size=(feats_input_size, 1)), dtype=np.float32)
deep_fm_bias = tf.Variable(tf.random_normal([1]))
out = tf.add(tf.matmul(feats_input, deep_fm_weight), deep_fm_bias)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2019)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
single_cate_feats = cate_feats[:, 0:params.cate_field_size]
multi_cate_feats = cate_feats[:, params.cate_field_size:]
cont_feats_index = tf.Variable([[i
for i in range(params.cont_field_size)]],
trainable=False,
dtype=tf.int64,
name="cont_feats_index")
cont_index_add = tf.add(cont_feats_index, params.cate_feats_size)
index_max_size = params.cont_field_size + params.cate_feats_size
feats_emb = my_layer.emb_init(name='feats_emb',
feat_num=index_max_size,
embedding_size=params.embedding_size)
# cont_feats -> Embedding
with tf.name_scope("cont_feat_emb"):
ori_cont_emb = tf.nn.embedding_lookup(feats_emb,
ids=cont_index_add,
name="ori_cont_emb")
cont_value = tf.reshape(cont_feats,
shape=[-1, params.cont_field_size, 1],
name="cont_value")
cont_emb = tf.multiply(ori_cont_emb, cont_value)
autoint_cont = cont_emb
cont_emb = tf.reshape(
cont_emb,
shape=[-1, params.cont_field_size * params.embedding_size],
name="cont_emb")
# single_category -> Embedding
with tf.name_scope("single_cate_emb"):
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=single_cate_feats)
autoint_cate = cate_emb
cate_emb = tf.reshape(
cate_emb,
shape=[-1, params.cate_field_size * params.embedding_size])
# multi_category -> Embedding
with tf.name_scope("multi_cate_emb"):
multi_cate_emb = my_layer.multi_cate_emb(params.multi_feats_range,
feats_emb, multi_cate_feats)
autoint_multi_cate = tf.reshape(
multi_cate_emb,
shape=[-1,
len(params.multi_feats_range), params.embedding_size])
# AutoInteracting
with tf.name_scope("AutoInt"):
autoint_input = tf.concat(
[autoint_cont, autoint_cate, autoint_multi_cate], axis=1)
for i in range(params.autoint_layer_num):
autoint_input = my_layer.InteractingLayer(
num_layer=i,
att_emb_size=params.autoint_emb_size,
seed=2020,
head_num=params.autoint_head_num,
use_res=params.autoint_use_res)(autoint_input)
autoint_output = tf.layers.Flatten()(autoint_input)
# deep input dense
dense = tf.concat([cont_emb, vector_feats, cate_emb, multi_cate_emb],
axis=1,
name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
dense = tf.layers.dense(inputs=dense,
units=params.hidden_units[i],
activation=tf.nn.relu)
final_input = tf.concat([autoint_output, dense], axis=1)
out = tf.layers.dense(inputs=final_input, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2020)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
cont_feats_index = tf.Variable(
[[i for i in range(params.cont_field_count)]],
trainable=False,
dtype=tf.int64,
name="cont_feats_index")
cont_feats_index = tf.add(cont_feats_index, params.cate_emb_space_size)
feats_size = params.cont_field_count + params.cate_emb_space_size
weights = dict()
weights["feats_emb"] = tf.get_variable(
name='feats_emb',
shape=[feats_size, params.embedding_size],
initializer=tf.glorot_normal_initializer())
weights["feats_bias"] = tf.get_variable(
name='feats_bias',
shape=[feats_size, 1],
initializer=tf.glorot_normal_initializer())
with tf.name_scope('fm_part'):
# FM_first_order [?, total_field_count]
first_cont_emb = tf.nn.embedding_lookup(
weights["feats_bias"], ids=cont_feats_index) # [None, F, 1]
first_cont_emb = tf.reshape(first_cont_emb,
shape=[-1, params.cont_field_count])
first_order = tf.multiply(first_cont_emb, cont_feats)
first_cate_emb = tf.nn.embedding_lookup(weights["feats_bias"],
ids=cate_feats)
first_cate_emb = tf.reshape(first_cate_emb,
shape=[-1, params.cate_field_count])
first_order = tf.concat([first_order, first_cate_emb], axis=1)
if params.multi_feats_type == 'dense':
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(
weights["feats_bias"],
ids=features[name_topN[0]]) # [None, topN, 1]
dense_embedding = tf.reduce_sum(dense_embedding,
axis=1) # [None, 1]
first_order = tf.concat([first_order, dense_embedding], axis=1)
else: # sparse
for name_topN in params.multi_cate_field_list:
sparse_embedding = tf.nn.embedding_lookup_sparse(
weights["feats_bias"],
sp_ids=features[name_topN[0]],
sp_weights=None,
combiner='sum') # [None, 1]
first_order = tf.concat([first_order, sparse_embedding],
axis=1)
# FM_second_order [?, embedding_size]
second_cont_emb = tf.nn.embedding_lookup(
weights["feats_emb"],
ids=cont_feats_index) # [None, F, embedding_size]
second_cont_value = tf.reshape(cont_feats,
shape=[-1, params.cont_field_count, 1])
embeddings = tf.multiply(second_cont_emb, second_cont_value)
second_cate_emb = tf.nn.embedding_lookup(weights["feats_emb"],
ids=cate_feats)
embeddings = tf.concat([embeddings, second_cate_emb],
axis=1) # [None, F, embedding_size]
if params.multi_feats_type == 'dense':
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(
weights["feats_emb"],
ids=features[name_topN[0]]) # [None, topN, embedding_size]
dense_embedding = tf.reduce_sum(
dense_embedding, axis=1) # [None, embedding_size]
dense_embedding = tf.reshape(
dense_embedding, shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, dense_embedding], axis=1)
else: # sparse
for name_topN in params.multi_cate_field_list:
sparse_embedding = tf.nn.embedding_lookup_sparse(
weights["feats_emb"],
sp_ids=features[name_topN[0]],
sp_weights=None,
combiner='sum') # [None, embedding_size]
sparse_embedding = tf.reshape(
sparse_embedding, shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, sparse_embedding], axis=1)
autoint_emb = embeddings
with tf.name_scope("AutoInt"):
for i in range(params.autoint_layer_count):
autoint_emb = my_layer.InteractingLayer(
num_layer=i,
att_emb_size=params.autoint_emb_size,
seed=2020,
head_num=params.autoint_head_count,
use_res=params.autoint_use_res
)(
autoint_emb
) # [None, F, head*autoint_emb_size] 令head*autoint_emb_size=embedding_size
embeddings = tf.concat([embeddings, autoint_emb], axis=1)
sum_emb = tf.reduce_sum(embeddings, 1)
sum_square_emb = tf.square(sum_emb)
square_emb = tf.square(embeddings)
square_sum_emb = tf.reduce_sum(square_emb, 1)
second_order = 0.5 * tf.subtract(sum_square_emb, square_sum_emb)
# print(second_order)
# FM_res [?, total_field_count + embedding_size]
fm_res = tf.concat([first_order, second_order], axis=1)
# deep_res including autoint
deep_res = tf.layers.flatten(embeddings)
wide = deep_res # wide including autoint
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
deep_res = tf.layers.dense(inputs=deep_res,
units=params.hidden_units[i],
activation=tf.nn.relu)
# fm & deep & wide
feats_input = tf.concat([fm_res, deep_res, wide], axis=1)
out = tf.layers.dense(inputs=feats_input, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2019)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
vector_feats = features["vector_feats"]
single_cate_feats = cate_feats[:, 0:params.cate_field_size]
multi_cate_feats = cate_feats[:, params.cate_field_size:]
cont_feats_index = tf.Variable([[i
for i in range(params.cont_field_size)]],
trainable=False,
dtype=tf.int64,
name="cont_feats_index")
cont_index_add = tf.add(cont_feats_index, params.cate_feats_size)
index_max_size = params.cont_field_size + params.cate_feats_size
feats_emb = my_layer.emb_init(name='feats_emb',
feat_num=index_max_size,
embedding_size=params.embedding_size)
# cont_feats -> Embedding
ori_cont_emb = tf.nn.embedding_lookup(feats_emb,
ids=cont_index_add,
name="ori_cont_emb")
cont_value = tf.reshape(cont_feats,
shape=[-1, params.cont_field_size, 1],
name="cont_value")
cont_emb = tf.multiply(ori_cont_emb, cont_value)
cont_emb = tf.reshape(
cont_emb,
shape=[-1, params.cont_field_size * params.embedding_size],
name="cont_emb")
# print(ori_cont_emb)
# print(cont_value)
# print(cont_emb)
# single_category -> Embedding
cate_emb = tf.nn.embedding_lookup(feats_emb, ids=single_cate_feats)
cate_emb = tf.reshape(
cate_emb, shape=[-1, params.cate_field_size * params.embedding_size])
# print(cate_emb)
# multi_category -> Embedding
multi_cate_emb = my_layer.multi_cate_emb(params.multi_feats_range,
feats_emb, multi_cate_feats)
# deep input dense
dense = tf.concat([cont_emb, vector_feats, cate_emb, multi_cate_emb],
axis=1,
name='dense_vector')
# deep
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
dense = tf.layers.dense(inputs=dense,
units=params.hidden_units[i],
activation=tf.nn.relu)
out = tf.layers.dense(inputs=dense, units=1)
score = tf.identity(tf.nn.sigmoid(out), name='score')
model_estimator_spec = op.model_optimizer(params, mode, labels, score)
return model_estimator_spec
def model_fn(labels, features, mode, params):
tf.set_random_seed(2020)
cont_feats = features["cont_feats"]
cate_feats = features["cate_feats"]
cont_feats_index = tf.Variable(
[[i for i in range(params.cont_field_count)]],
trainable=False,
dtype=tf.int64,
name="cont_feats_index")
cont_feats_index = tf.add(cont_feats_index, params.cate_emb_space_size)
feats_size = params.cont_field_count + params.cate_emb_space_size
weights = dict()
weights["feats_emb"] = tf.get_variable(
name='feats_emb',
shape=[feats_size, params.embedding_size],
initializer=tf.glorot_normal_initializer())
weights["feats_bias"] = tf.get_variable(
name='feats_bias',
shape=[feats_size, 1],
initializer=tf.glorot_normal_initializer())
with tf.name_scope('fm_part'):
# FM_first_order [?, total_field_count]
first_cont_emb = tf.nn.embedding_lookup(
weights["feats_bias"], ids=cont_feats_index) # [None, F, 1]
first_cont_emb = tf.reshape(first_cont_emb,
shape=[-1, params.cont_field_count])
first_order = tf.multiply(first_cont_emb, cont_feats)
first_cate_emb = tf.nn.embedding_lookup(weights["feats_bias"],
ids=cate_feats)
first_cate_emb = tf.reshape(first_cate_emb,
shape=[-1, params.cate_field_count])
first_order = tf.concat([first_order, first_cate_emb], axis=1)
if params.multi_feats_type == 'dense':
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(
weights["feats_bias"],
ids=features[name_topN[0]]) # [None, topN, 1]
dense_embedding = tf.reduce_sum(dense_embedding,
axis=1) # [None, 1]
first_order = tf.concat([first_order, dense_embedding], axis=1)
else: # sparse
for name_topN in params.multi_cate_field_list:
sparse_embedding = tf.nn.embedding_lookup_sparse(
weights["feats_bias"],
sp_ids=features[name_topN[0]],
sp_weights=None,
combiner='sum') # [None, 1]
first_order = tf.concat([first_order, sparse_embedding],
axis=1)
# FM_second_order [?, embedding_size]
second_cont_emb = tf.nn.embedding_lookup(
weights["feats_emb"],
ids=cont_feats_index) # [None, F, embedding_size]
second_cont_value = tf.reshape(cont_feats,
shape=[-1, params.cont_field_count, 1])
embeddings = tf.multiply(second_cont_emb, second_cont_value)
second_cate_emb = tf.nn.embedding_lookup(weights["feats_emb"],
ids=cate_feats)
embeddings = tf.concat([embeddings, second_cate_emb],
axis=1) # [None, F, embedding_size]
if params.multi_feats_type == 'dense':
for name_topN in params.multi_cate_field_list:
dense_embedding = tf.nn.embedding_lookup(
weights["feats_emb"],
ids=features[name_topN[0]]) # [None, topN, embedding_size]
dense_embedding = tf.reduce_sum(
dense_embedding, axis=1) # [None, embedding_size]
dense_embedding = tf.reshape(
dense_embedding, shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, dense_embedding], axis=1)
else: # sparse
for name_topN in params.multi_cate_field_list:
sparse_embedding = tf.nn.embedding_lookup_sparse(
weights["feats_emb"],
sp_ids=features[name_topN[0]],
sp_weights=None,
combiner='sum') # [None, embedding_size]
sparse_embedding = tf.reshape(
sparse_embedding, shape=[-1, 1, params.embedding_size])
embeddings = tf.concat([embeddings, sparse_embedding], axis=1)
sum_emb = tf.reduce_sum(embeddings, 1)
sum_square_emb = tf.square(sum_emb)
square_emb = tf.square(embeddings)
square_sum_emb = tf.reduce_sum(square_emb, 1)
second_order = 0.5 * tf.subtract(sum_square_emb, square_sum_emb)
# print(second_order)
# FM_res [?, total_field_count + embedding_size]
fm_res = tf.concat([first_order, second_order], axis=1)
with tf.name_scope('deep_part'):
deep_res = tf.reshape(
embeddings,
shape=[-1, params.total_field_count * params.embedding_size])
len_layers = len(params.hidden_units)
for i in range(0, len_layers):
deep_res = tf.layers.dense(inputs=deep_res,
units=params.hidden_units[i],
activation=tf.nn.relu)
with tf.name_scope('deep_fm'):
input_size = params.total_field_count + params.embedding_size + params.hidden_units[
-1] # FM_res->total_field_count+embedding_size, Deep_res->hidden_units[-1]
weights["concat_emb"] = tf.get_variable(
name='concat_emb',
shape=[input_size, 1],
initializer=tf.glorot_normal_initializer())
weights["concat_bias"] = tf.get_variable(
name='concat_bias',
shape=[1],
initializer=tf.constant_initializer(0.01))
feats_input = tf.concat([fm_res, deep_res], axis=1)
out = tf.add(tf.matmul(feats_input, weights["concat_emb"]),
weights["concat_bias"])
y = tf.nn.sigmoid(out)
model_estimator_spec = op.model_optimizer(params, mode, labels, y)
return model_estimator_spec
