Bert结构代码阅读笔记

Bert论文：link

Bert结构：

具体可见colab: link

BertModel(
  (embeddings): BertEmbeddings(
    (word_embeddings): Embedding(30522, 768, padding_idx=0)
    (position_embeddings): Embedding(512, 768)
    (token_type_embeddings): Embedding(2, 768)
    (LayerNorm): BertLayerNorm()
    (dropout): Dropout(p=0.1)
  )
  (encoder): BertEncoder(
    (layer): ModuleList(
      (0): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (1): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (2): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (3): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (4): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (5): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (6): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (7): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (8): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (9): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (10): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
      (11): BertLayer(
        (attention): BertAttention(
          (self): BertSelfAttention(
            (query): Linear(in_features=768, out_features=768, bias=True)
            (key): Linear(in_features=768, out_features=768, bias=True)
            (value): Linear(in_features=768, out_features=768, bias=True)
            (dropout): Dropout(p=0.1)
          )
          (output): BertSelfOutput(
            (dense): Linear(in_features=768, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (intermediate): BertIntermediate(
          (dense): Linear(in_features=768, out_features=3072, bias=True)
        )
        (output): BertOutput(
          (dense): Linear(in_features=3072, out_features=768, bias=True)
          (LayerNorm): BertLayerNorm()
          (dropout): Dropout(p=0.1)
        )
      )
    )
  )
  (pooler): BertPooler(
    (dense): Linear(in_features=768, out_features=768, bias=True)
    (activation): Tanh()
  )
)

Bert代码 参考：link

1. Bert配置文件，bert-base-uncased为例

{
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu", # 激活函数
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 512,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

2.BertModel类

总体设计：
顺序关系：embedding，encoder，pooler层，输出：output

class BertModel(BertPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.config = config

        self.embeddings = BertEmbeddings(config)
        self.encoder = BertEncoder(config)
        self.pooler = BertPooler(config)

        self.init_weights()
        
 def forward(
        self, input_ids=None, attention_mask=None, token_type_ids=None,
        position_ids=None, head_mask=None, inputs_embeds=None,
        encoder_hidden_states=None, encoder_attention_mask=None,
    ):
    """ 省略部分代码 """
    
        embedding_output = self.embeddings(
            input_ids=input_ids, position_ids=position_ids, token_type_ids=token_type_ids, inputs_embeds=inputs_embeds
        )
        encoder_outputs = self.encoder(
            embedding_output,
            attention_mask=extended_attention_mask,
            head_mask=head_mask,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_extended_attention_mask,
        ) # encoder具体形式是一个tuple，每个元素是每层的输出（bacth_size * seq_length * hidden_size), 具体顺序见encoder的实现
        sequence_output = encoder_outputs[0] # 取出encoder最后一层的的输出
        pooled_output = self.pooler(sequence_output) # 对最后一层的结果的第一个（CLS）做polling，即fc+tanh

        outputs = (sequence_output, pooled_output,) + encoder_outputs[ # 这个可有可无，取决前11层和输入层要不要返回
            1:
        ]  # add hidden_states and attentions if they are here
        return outputs  # sequence_output, pooled_output, (hidden_states), (attentions)```

3. BertEmbeddings

embedding是inputs_embeds，position_embeddings 与token_type_embeddings之和，均为矩阵运算得来

def __init__(self, config):
        super().__init__()
        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=0)
        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
        self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)
        # self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
        # any TensorFlow checkpoint file
        self.LayerNorm = BertLayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)
        
def forward(self, input_ids=None, token_type_ids=None, position_ids=None, inputs_embeds=None):
        """ 省略 embedding生成过程 """
          
        embeddings = inputs_embeds + position_embeddings + token_type_embeddings
        embeddings = self.LayerNorm(embeddings)
        embeddings = self.dropout(embeddings)
        return embeddings

4. BertEncoder

class BertEncoder(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.output_attentions = config.output_attentions
        self.output_hidden_states = config.output_hidden_states
        self.layer = nn.ModuleList([BertLayer(config) for _ in range(config.num_hidden_layers)])

    def forward(
        self,
        hidden_states,
        attention_mask=None,
        head_mask=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
    ):
        all_hidden_states = () # 保存输入层，中间隐含层，和输出层
        all_attentions = ()
        for i, layer_module in enumerate(self.layer):
            if self.output_hidden_states:
                all_hidden_states = all_hidden_states + (hidden_states,) # 保存每一层的输出

            layer_outputs = layer_module(
                hidden_states, attention_mask, head_mask[i], encoder_hidden_states, encoder_attention_mask
            )
            hidden_states = layer_outputs[0]

            if self.output_attentions:
                all_attentions = all_attentions + (layer_outputs[1],)

        # Add last layer
        if self.output_hidden_states:
            all_hidden_states = all_hidden_states + (hidden_states,) 

        outputs = (hidden_states,)
        if self.output_hidden_states:
            outputs = outputs + (all_hidden_states,)
        if self.output_attentions:
            outputs = outputs + (all_attentions,)
        return outputs  # last-layer hidden state, (all hidden states), (all attentions)

5. BertPooler

class BertPooler(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
        self.activation = nn.Tanh()

    def forward(self, hidden_states):
        # We "pool" the model by simply taking the hidden state corresponding
        # to the first token.
        first_token_tensor = hidden_states[:, 0] # 只操作了最后一层的第一个token位
        pooled_output = self.dense(first_token_tensor)
        pooled_output = self.activation(pooled_output)
        return pooled_output

6. summary

这是bert的总体实现思路，具体到下游任务，还需要对output进行微调。
总体修改思路是：CLS用于判定句子整体的属性，在这种情况下：最后一层的pooler也是只对CLS操作，用于分类。
在MLM，NER等任务的时候，需要对其他的token也做pooler操作，然后加上全连接层。主要看那个token在进行分类