bert文本分类——单标签与多标签对比

单标签：

def create_model_original(bert_config, is_training, input_ids, input_mask, segment_ids, labels, num_labels, use_one_hot_embeddings):
  """Creates a classification model."""
  model = modeling.BertModel(
      config=bert_config,
      is_training=is_training,
      input_ids=input_ids,
      input_mask=input_mask,
      token_type_ids=segment_ids,
      use_one_hot_embeddings=use_one_hot_embeddings)

  output_layer = model.get_pooled_output() # 从主干模型获得模型的输出

  hidden_size = output_layer.shape[-1].value

  output_weights = tf.get_variable( # 分类模型特有的分类层的参数
      "output_weights", [num_labels, hidden_size],
      initializer=tf.truncated_normal_initializer(stddev=0.02))

  output_bias = tf.get_variable( # 分类模型特有的bias
      "output_bias", [num_labels], initializer=tf.zeros_initializer())

  with tf.variable_scope("loss"):