def create_embedding_dict(sparse_feature_columns,
varlen_sparse_feature_columns,
seed,
l2_reg,
prefix='sparse_',
seq_mask_zero=True):
sparse_embedding = {}
for feat in sparse_feature_columns:
emb = Embedding(feat.vocabulary_size,
feat.embedding_dim,
embeddings_initializer=feat.embeddings_initializer,
embeddings_regularizer=l2(l2_reg),
name=prefix + '_emb_' + feat.embedding_name)
emb.trainable = feat.trainable
sparse_embedding[feat.embedding_name] = emb
if varlen_sparse_feature_columns and len(
varlen_sparse_feature_columns) > 0:
for feat in varlen_sparse_feature_columns:
# if feat.name not in sparse_embedding:
emb = Embedding(feat.vocabulary_size,
feat.embedding_dim,
embeddings_initializer=feat.embeddings_initializer,
embeddings_regularizer=l2(l2_reg),
name=prefix + '_seq_emb_' + feat.name,
mask_zero=seq_mask_zero)
emb.trainable = feat.trainable
sparse_embedding[feat.embedding_name] = emb
return sparse_embedding
def create_embedding_dict(sparse_feature_columns,
varlen_sparse_feature_columns,
seed,
l2_reg,
prefix='sparse_',
seq_mask_zero=True):
"""
name -> embedding layer
没法加载预训练的embedding参数
@ Warning! varlen_sparse_feature_columns即使使用跟sparse_feature_columns相同的特征，eg（历史行为序列），也是不同的embedding层!!! @
"""
sparse_embedding = {}
for feat in sparse_feature_columns:
emb = Embedding(feat.vocabulary_size,
feat.embedding_dim,
embeddings_initializer=feat.embeddings_initializer,
embeddings_regularizer=l2(l2_reg),
name=prefix + '_emb_' + feat.embedding_name)
emb.trainable = feat.trainable
sparse_embedding[feat.embedding_name] = emb
if varlen_sparse_feature_columns and len(
varlen_sparse_feature_columns) > 0:
for feat in varlen_sparse_feature_columns:
# if feat.name not in sparse_embedding:
emb = Embedding(feat.vocabulary_size,
feat.embedding_dim,
embeddings_initializer=feat.embeddings_initializer,
embeddings_regularizer=l2(l2_reg),
name=prefix + '_seq_emb_' + feat.name,
mask_zero=seq_mask_zero)
emb.trainable = feat.trainable
sparse_embedding[feat.embedding_name] = emb
return sparse_embedding
def create_embedding_dict(sparse_feature_columns ,seed, l2_reg,
prefix='sparse_', seq_mask_zero=True):
#将特征进行embedding ,输入维度是某个特征的种类数
sparse_embedding = {}
for feat in sparse_feature_columns:
emb = Embedding(feat.vocabulary_size, feat.embedding_dim,
embeddings_initializer=feat.embeddings_initializer,
embeddings_regularizer=l2(l2_reg),
name=prefix + '_emb_' + feat.embedding_name)
emb.trainable = feat.trainable
sparse_embedding[feat.embedding_name] = emb
return sparse_embedding
