def MIND(user_feature_columns,
item_feature_columns,
num_sampled=5,
k_max=2,
p=1.0,
dynamic_k=False,
user_dnn_hidden_units=(64, 32),
dnn_activation='relu',
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024):
"""Instantiates the MIND Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param num_sampled: int, the number of classes to randomly sample per batch.
:param k_max: int, the max size of user interest embedding
:param p: float,the parameter for adjusting the attention distribution in LabelAwareAttention.
:param dynamic_k: bool, whether or not use dynamic interest number
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param user_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of user tower
:param dnn_activation: Activation function to use in deep net
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param l2_reg_dnn: L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:return: A Keras model instance.
"""
if len(item_feature_columns) > 1:
raise ValueError("Now MIND only support 1 item feature like item_id")
item_feature_column = item_feature_columns[0]
item_feature_name = item_feature_column.name
item_vocabulary_size = item_feature_columns[0].vocabulary_size
item_embedding_dim = item_feature_columns[0].embedding_dim
# item_index = Input(tensor=tf.constant([list(range(item_vocabulary_size))]))
history_feature_list = [item_feature_name]
features = build_input_features(user_feature_columns)
sparse_feature_columns = list(
filter(lambda x: isinstance(x, SparseFeat),
user_feature_columns)) if user_feature_columns else []
dense_feature_columns = list(
filter(lambda x: isinstance(x, DenseFeat),
user_feature_columns)) if user_feature_columns else []
varlen_sparse_feature_columns = list(
filter(lambda x: isinstance(x, VarLenSparseFeat),
user_feature_columns)) if user_feature_columns else []
history_feature_columns = []
sparse_varlen_feature_columns = []
history_fc_names = list(map(lambda x: "hist_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in history_fc_names:
history_feature_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
seq_max_len = history_feature_columns[0].maxlen
inputs_list = list(features.values())
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix="")
item_features = build_input_features(item_feature_columns)
query_emb_list = embedding_lookup(embedding_matrix_dict,
item_features,
item_feature_columns,
history_feature_list,
history_feature_list,
to_list=True)
keys_emb_list = embedding_lookup(embedding_matrix_dict,
features,
history_feature_columns,
history_fc_names,
history_fc_names,
to_list=True)
dnn_input_emb_list = embedding_lookup(embedding_matrix_dict,
features,
sparse_feature_columns,
mask_feat_list=history_feature_list,
to_list=True)
dense_value_list = get_dense_input(features, dense_feature_columns)
sequence_embed_dict = varlen_embedding_lookup(
embedding_matrix_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
dnn_input_emb_list += sequence_embed_list
# keys_emb = concat_func(keys_emb_list, mask=True)
# query_emb = concat_func(query_emb_list, mask=True)
history_emb = PoolingLayer()(NoMask()(keys_emb_list))
target_emb = PoolingLayer()(NoMask()(query_emb_list))
# target_emb_size = target_emb.get_shape()[-1].value
# max_len = history_emb.get_shape()[1].value
hist_len = features['hist_len']
high_capsule = CapsuleLayer(input_units=item_embedding_dim,
out_units=item_embedding_dim,
max_len=seq_max_len,
k_max=k_max)((history_emb, hist_len))
if len(dnn_input_emb_list) > 0 or len(dense_value_list) > 0:
user_other_feature = combined_dnn_input(dnn_input_emb_list,
dense_value_list)
other_feature_tile = tf.keras.layers.Lambda(
tile_user_otherfeat, arguments={'k_max':
k_max})(user_other_feature)
user_deep_input = Concatenate()(
[NoMask()(other_feature_tile), high_capsule])
else:
user_deep_input = high_capsule
user_embeddings = DNN(user_dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
name="user_embedding")(user_deep_input)
item_inputs_list = list(item_features.values())
item_embedding_matrix = embedding_matrix_dict[item_feature_name]
item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(
item_features[item_feature_name])
item_embedding_weight = NoMask()(item_embedding_matrix(item_index))
pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
if dynamic_k:
user_embedding_final = LabelAwareAttention(
k_max=k_max,
pow_p=p,
)((user_embeddings, target_emb, hist_len))
else:
user_embedding_final = LabelAwareAttention(
k_max=k_max,
pow_p=p,
)((user_embeddings, target_emb))
output = SampledSoftmaxLayer(num_sampled=num_sampled)([
pooling_item_embedding_weight, user_embedding_final,
item_features[item_feature_name]
])
model = Model(inputs=inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", inputs_list)
model.__setattr__("user_embedding", user_embeddings)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__(
"item_embedding",
get_item_embedding(pooling_item_embedding_weight,
item_features[item_feature_name]))
return model
def FM(user_feature_columns,
item_feature_columns,
l2_reg_embedding=1e-6,
init_std=0.0001,
seed=1024,
metric='cos'):
"""Instantiates the FM architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param metric: str, ``"cos"`` for cosine or ``"ip"`` for inner product
:return: A Keras model instance.
"""
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
seq_mask_zero=True)
user_features = build_input_features(user_feature_columns)
user_inputs_list = list(user_features.values())
user_sparse_embedding_list, user_dense_value_list = input_from_feature_columns(
user_features,
user_feature_columns,
l2_reg_embedding,
init_std,
seed,
support_dense=False,
embedding_matrix_dict=embedding_matrix_dict)
item_features = build_input_features(item_feature_columns)
item_inputs_list = list(item_features.values())
item_sparse_embedding_list, item_dense_value_list = input_from_feature_columns(
item_features,
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
support_dense=False,
embedding_matrix_dict=embedding_matrix_dict)
user_dnn_input = concat_func(user_sparse_embedding_list, axis=1)
user_vector_sum = Lambda(lambda x: reduce_sum(x, axis=1, keep_dims=False))(
user_dnn_input)
item_dnn_input = concat_func(item_sparse_embedding_list, axis=1)
item_vector_sum = Lambda(lambda x: reduce_sum(x, axis=1, keep_dims=False))(
item_dnn_input)
score = Similarity(type=metric)([user_vector_sum, item_vector_sum])
output = PredictionLayer("binary", False)(score)
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("user_embedding", user_vector_sum)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__("item_embedding", item_vector_sum)
return model
def DSSM(user_feature_columns,
item_feature_columns,
user_dnn_hidden_units=(64, 32),
item_dnn_hidden_units=(64, 32),
dnn_activation='tanh',
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
metric='cos'):
"""Instantiates the Deep Structured Semantic Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param user_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of user tower
:param item_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of item tower
:param dnn_activation: Activation function to use in deep net
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param metric: str, ``"cos"`` for cosine or ``"ip"`` for inner product
:return: A Keras model instance.
"""
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
seq_mask_zero=True)
user_features = build_input_features(user_feature_columns)
user_inputs_list = list(user_features.values())
user_sparse_embedding_list, user_dense_value_list = input_from_feature_columns(
user_features,
user_feature_columns,
l2_reg_embedding,
init_std,
seed,
embedding_matrix_dict=embedding_matrix_dict)
user_dnn_input = combined_dnn_input(user_sparse_embedding_list,
user_dense_value_list)
item_features = build_input_features(item_feature_columns)
item_inputs_list = list(item_features.values())
item_sparse_embedding_list, item_dense_value_list = input_from_feature_columns(
item_features,
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
embedding_matrix_dict=embedding_matrix_dict)
item_dnn_input = combined_dnn_input(item_sparse_embedding_list,
item_dense_value_list)
user_dnn_out = DNN(
user_dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
)(user_dnn_input)
item_dnn_out = DNN(item_dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(item_dnn_input)
score = Similarity(type=metric)([user_dnn_out, item_dnn_out])
output = PredictionLayer("binary", False)(score)
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__("user_embedding", user_dnn_out)
model.__setattr__("item_embedding", item_dnn_out)
return model
def NCF(user_feature_columns,
item_feature_columns,
user_gmf_embedding_dim=20,
item_gmf_embedding_dim=20,
user_mlp_embedding_dim=20,
item_mlp_embedding_dim=20,
dnn_use_bn=False,
dnn_hidden_units=(64, 32),
dnn_activation='relu',
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024):
"""Instantiates the NCF Model architecture.
:param user_feature_columns: A dict containing user's features and features'dim.
:param item_feature_columns: A dict containing item's features and features'dim.
:param user_gmf_embedding_dim: int.
:param item_gmf_embedding_dim: int.
:param user_mlp_embedding_dim: int.
:param item_mlp_embedding_dim: int.
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param dnn_activation: Activation function to use in deep net
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:return: A Keras model instance.
"""
user_dim = len(user_feature_columns) * user_gmf_embedding_dim
item_dim = len(item_feature_columns) * item_gmf_embedding_dim
dim = (user_dim * item_dim) / (math.gcd(user_dim, item_dim))
user_gmf_embedding_dim = int(dim / len(user_feature_columns))
item_gmf_embedding_dim = int(dim / len(item_feature_columns))
# Generalized Matrix Factorization (GMF) Part
user_gmf_feature_columns = [
SparseFeat(feat,
vocabulary_size=size,
embedding_dim=user_gmf_embedding_dim)
for feat, size in user_feature_columns.items()
]
user_features = build_input_features(user_gmf_feature_columns)
user_inputs_list = list(user_features.values())
user_gmf_sparse_embedding_list, user_gmf_dense_value_list = input_from_feature_columns(
user_features,
user_gmf_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix='gmf_')
user_gmf_input = combined_dnn_input(user_gmf_sparse_embedding_list, [])
user_gmf_out = Lambda(lambda x: x,
name="user_gmf_embedding")(user_gmf_input)
item_gmf_feature_columns = [
SparseFeat(feat,
vocabulary_size=size,
embedding_dim=item_gmf_embedding_dim)
for feat, size in item_feature_columns.items()
]
item_features = build_input_features(item_gmf_feature_columns)
item_inputs_list = list(item_features.values())
item_gmf_sparse_embedding_list, item_gmf_dense_value_list = input_from_feature_columns(
item_features,
item_gmf_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix='gmf_')
item_gmf_input = combined_dnn_input(item_gmf_sparse_embedding_list, [])
item_gmf_out = Lambda(lambda x: x,
name="item_gmf_embedding")(item_gmf_input)
gmf_out = Multiply()([user_gmf_out, item_gmf_out])
# Multi-Layer Perceptron (MLP) Part
user_mlp_feature_columns = [
SparseFeat(feat,
vocabulary_size=size,
embedding_dim=user_mlp_embedding_dim)
for feat, size in user_feature_columns.items()
]
user_mlp_sparse_embedding_list, user_mlp_dense_value_list = input_from_feature_columns(
user_features,
user_mlp_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix='mlp_')
user_mlp_input = combined_dnn_input(user_mlp_sparse_embedding_list,
user_mlp_dense_value_list)
user_mlp_out = Lambda(lambda x: x,
name="user_mlp_embedding")(user_mlp_input)
item_mlp_feature_columns = [
SparseFeat(feat,
vocabulary_size=size,
embedding_dim=item_mlp_embedding_dim)
for feat, size in item_feature_columns.items()
]
item_mlp_sparse_embedding_list, item_mlp_dense_value_list = input_from_feature_columns(
item_features,
item_mlp_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix='mlp_')
item_mlp_input = combined_dnn_input(item_mlp_sparse_embedding_list,
item_mlp_dense_value_list)
item_mlp_out = Lambda(lambda x: x,
name="item_mlp_embedding")(item_mlp_input)
mlp_input = Concatenate(axis=1)([user_mlp_out, item_mlp_out])
mlp_out = DNN(dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
name="mlp_embedding")(mlp_input)
# Fusion of GMF and MLP
neumf_input = Concatenate(axis=1)([gmf_out, mlp_out])
neumf_out = DNN(hidden_units=[1], activation='sigmoid')(neumf_input)
output = Lambda(lambda x: x, name='neumf_out')(neumf_out)
# output = PredictionLayer(task, False)(neumf_out)
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
return model
def SDM(user_feature_columns,
item_feature_columns,
history_feature_list,
num_sampled=5,
units=64,
rnn_layers=2,
dropout_rate=0.2,
rnn_num_res=1,
num_head=4,
l2_reg_embedding=1e-6,
dnn_activation='tanh',
init_std=0.0001,
seed=1024):
"""Instantiates the Sequential Deep Matching Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param history_feature_list: list,to indicate short and prefer sequence sparse field
:param num_sampled: int, the number of classes to randomly sample per batch.
:param units: int, dimension for each output layer
:param rnn_layers: int, layer number of rnn
:param dropout_rate: float in [0,1), the probability we will drop out a given DNN coordinate.
:param rnn_num_res: int. The number of residual layers in rnn layers
:param num_head: int int, the number of attention head
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_activation: Activation function to use in deep net
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:return: A Keras model instance.
"""
if len(item_feature_columns) > 1:
raise ValueError("Now MIND only support 1 item feature like item_id")
item_feature_column = item_feature_columns[0]
item_feature_name = item_feature_column.name
item_vocabulary_size = item_feature_columns[0].vocabulary_size
features = build_input_features(user_feature_columns)
user_inputs_list = list(features.values())
sparse_feature_columns = list(
filter(lambda x: isinstance(x, SparseFeat),
user_feature_columns)) if user_feature_columns else []
dense_feature_columns = list(
filter(lambda x: isinstance(x, DenseFeat),
user_feature_columns)) if user_feature_columns else []
if len(dense_feature_columns) != 0:
raise ValueError("Now SDM don't support dense feature")
varlen_sparse_feature_columns = list(
filter(lambda x: isinstance(x, VarLenSparseFeat),
user_feature_columns)) if user_feature_columns else []
sparse_varlen_feature_columns = []
prefer_history_columns = []
short_history_columns = []
prefer_fc_names = list(map(lambda x: "prefer_" + x, history_feature_list))
short_fc_names = list(map(lambda x: "short_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in prefer_fc_names:
prefer_history_columns.append(fc)
elif feature_name in short_fc_names:
short_history_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix="")
item_features = build_input_features(item_feature_columns)
item_inputs_list = list(item_features.values())
prefer_emb_list = embedding_lookup(embedding_matrix_dict,
features,
prefer_history_columns,
prefer_fc_names,
prefer_fc_names,
to_list=True) # L^u
short_emb_list = embedding_lookup(embedding_matrix_dict,
features,
short_history_columns,
short_fc_names,
short_fc_names,
to_list=True) # S^u
# dense_value_list = get_dense_input(features, dense_feature_columns)
user_emb_list = embedding_lookup(embedding_matrix_dict,
features,
sparse_feature_columns,
to_list=True)
sequence_embed_dict = varlen_embedding_lookup(
embedding_matrix_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
user_emb_list += sequence_embed_list # e^u
# if len(user_emb_list) > 0 or len(dense_value_list) > 0:
# user_emb_feature = combined_dnn_input(user_emb_list, dense_value_list)
user_emb = concat_func(user_emb_list)
user_emb_output = Dense(units,
activation=dnn_activation,
name="user_emb_output")(user_emb)
prefer_sess_length = features['prefer_sess_length']
prefer_att_outputs = []
for i, prefer_emb in enumerate(prefer_emb_list):
prefer_attention_output = AttentionSequencePoolingLayer(
dropout_rate=0)([user_emb_output, prefer_emb, prefer_sess_length])
prefer_att_outputs.append(prefer_attention_output)
prefer_att_concat = concat_func(prefer_att_outputs)
prefer_output = Dense(units,
activation=dnn_activation,
name="prefer_output")(prefer_att_concat)
short_sess_length = features['short_sess_length']
short_emb_concat = concat_func(short_emb_list)
short_emb_input = Dense(units,
activation=dnn_activation,
name="short_emb_input")(short_emb_concat)
short_rnn_output = DynamicMultiRNN(
num_units=units,
return_sequence=True,
num_layers=rnn_layers,
num_residual_layers=rnn_num_res,
dropout_rate=dropout_rate)([short_emb_input, short_sess_length])
short_att_output = SelfMultiHeadAttention(
num_units=units,
head_num=num_head,
dropout_rate=dropout_rate,
future_binding=True,
use_layer_norm=True)([short_rnn_output, short_sess_length
]) # [batch_size, time, num_units]
short_output = UserAttention(num_units=units, activation=dnn_activation, use_res=True, dropout_rate=dropout_rate) \
([user_emb_output, short_att_output, short_sess_length])
gate_input = concat_func([prefer_output, short_output, user_emb_output])
gate = Dense(units, activation='sigmoid')(gate_input)
gate_output = Lambda(
lambda x: tf.multiply(x[0], x[1]) + tf.multiply(1 - x[0], x[2]))(
[gate, short_output, prefer_output])
gate_output_reshape = Lambda(lambda x: tf.squeeze(x, 1))(gate_output)
item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(
item_features[item_feature_name])
item_embedding_matrix = embedding_matrix_dict[item_feature_name]
item_embedding_weight = NoMask()(item_embedding_matrix(item_index))
pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
output = SampledSoftmaxLayer(num_sampled=num_sampled)([
pooling_item_embedding_weight, gate_output_reshape,
item_features[item_feature_name]
])
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("user_embedding", gate_output_reshape)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__(
"item_embedding",
get_item_embedding(pooling_item_embedding_weight,
item_features[item_feature_name]))
return model
def YoutubeDNN(
user_feature_columns,
item_feature_columns,
num_sampled=5,
user_dnn_hidden_units=(64, 32),
dnn_activation='relu',
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
):
"""Instantiates the YoutubeDNN Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param num_sampled: int, the number of classes to randomly sample per batch.
:param user_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of user tower
:param dnn_activation: Activation function to use in deep net
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:return: A Keras model instance.
"""
if len(item_feature_columns) > 1:
raise ValueError(
"Now YoutubeNN only support 1 item feature like item_id")
item_feature_name = item_feature_columns[0].name
item_vocabulary_size = item_feature_columns[0].vocabulary_size
#构建User和 item 的 Embedding dict
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix="")
#构建 User Input dict
user_features = build_input_features(user_feature_columns)
user_inputs_list = list(user_features.values())
user_sparse_embedding_list, user_dense_value_list = input_from_feature_columns(
user_features,
user_feature_columns,
l2_reg_embedding,
init_std,
seed,
embedding_matrix_dict=embedding_matrix_dict)
user_dnn_input = combined_dnn_input(user_sparse_embedding_list,
user_dense_value_list)
# 构建 item Input dict
item_features = build_input_features(item_feature_columns)
item_inputs_list = list(item_features.values())
user_dnn_out = DNN(
user_dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
)(user_dnn_input)
print(item_features[item_feature_name])
print(list(range(item_vocabulary_size)))
item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(
item_features[item_feature_name])
item_embedding_matrix = embedding_matrix_dict[item_feature_name]
print(item_embedding_matrix(item_index))
item_embedding_weight = NoMask()(item_embedding_matrix(item_index))
pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
# tf.nn.sampled_softmax_loss,在类别很多的情况下训练softmax分类器的高效的方法。
# 注意：仅在训练时使用这一采样操作，测试时还是用全部的类别
output = SampledSoftmaxLayer(num_sampled=num_sampled)([
pooling_item_embedding_weight, user_dnn_out,
item_features[item_feature_name]
])
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("user_embedding", user_dnn_out)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__(
"item_embedding",
get_item_embedding(pooling_item_embedding_weight,
item_features[item_feature_name]))
return model