昨天同事突然問我"BERT論文中的圖，雖然畫了多個transformer block，但一層是不是相當於只有一個？？",我當時也有點懵逼,後來看了源碼弄清楚了,今天就寫一下
Bert整個代碼
class BertModel(BertPreTrainedModel):
"""
The model can behave as an encoder (with only self-attention) as well
as a decoder, in which case a layer of cross-attention is added between
the self-attention layers, following the architecture described in `Attention is all you need`_ by Ashish Vaswani,
Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.
To behave as an decoder the model needs to be initialized with the
:obj:`is_decoder` argument of the configuration set to :obj:`True`; an
:obj:`encoder_hidden_states` is expected as an input to the forward pass.
.. _`Attention is all you need`:
https://arxiv.org/abs/1706.03762
"""
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 get_input_embeddings(self):
return self.embeddings.word_embeddings
def set_input_embeddings(self, value):
self.embeddings.word_embeddings = value
def _prune_heads(self, heads_to_prune):
""" Prunes heads of the model.
heads_to_prune: dict of {layer_num: list of heads to prune in this layer}
See base class PreTrainedModel
"""
for layer, heads in heads_to_prune.items():
self.encoder.layer[layer].attention.prune_heads(heads)
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
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,
):
r"""
Return:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
last_hidden_state (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
pooler_output (:obj:`torch.FloatTensor`: of shape :obj:`(batch_size, hidden_size)`):
Last layer hidden-state of the first token of the sequence (classification token)
further processed by a Linear layer and a Tanh activation function. The Linear
layer weights are trained from the next sentence prediction (classification)
objective during pre-training.
This output is usually *not* a good summary
of the semantic content of the input, you're often better with averaging or pooling
the sequence of hidden-states for the whole input sequence.
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(batch_size, num_heads, sequence_length, sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
Examples::
from transformers import BertModel, BertTokenizer
import torch
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
last_hidden_states = outputs[0] # The last hidden-state is the first element of the output tuple
"""
if input_ids is not None and inputs_embeds is not None:
raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
elif input_ids is not None:
input_shape = input_ids.size()
elif inputs_embeds is not None:
input_shape = inputs_embeds.size()[:-1]
else:
raise ValueError("You have to specify either input_ids or inputs_embeds")
device = input_ids.device if input_ids is not None else inputs_embeds.device
if attention_mask is None:
attention_mask = torch.ones(input_shape, device=device)
if token_type_ids is None:
token_type_ids = torch.zeros(input_shape, dtype=torch.long, device=device)
# We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
# ourselves in which case we just need to make it broadcastable to all heads.
if attention_mask.dim() == 3:
extended_attention_mask = attention_mask[:, None, :, :]
elif attention_mask.dim() == 2:
# Provided a padding mask of dimensions [batch_size, seq_length]
# - if the model is a decoder, apply a causal mask in addition to the padding mask
# - if the model is an encoder, make the mask broadcastable to [batch_size, num_heads, seq_length, seq_length]
if self.config.is_decoder:
batch_size, seq_length = input_shape
seq_ids = torch.arange(seq_length, device=device)
causal_mask = seq_ids[None, None, :].repeat(batch_size, seq_length, 1) <= seq_ids[None, :, None]
causal_mask = causal_mask.to(
attention_mask.dtype
) # causal and attention masks must have same type with pytorch version < 1.3
extended_attention_mask = causal_mask[:, None, :, :] * attention_mask[:, None, None, :]
else:
extended_attention_mask = attention_mask[:, None, None, :]
else:
raise ValueError(
"Wrong shape for input_ids (shape {}) or attention_mask (shape {})".format(
input_shape, attention_mask.shape
)
)
# Since attention_mask is 1.0 for positions we want to attend and 0.0 for
# masked positions, this operation will create a tensor which is 0.0 for
# positions we want to attend and -10000.0 for masked positions.
# Since we are adding it to the raw scores before the softmax, this is
# effectively the same as removing these entirely.
extended_attention_mask = extended_attention_mask.to(dtype=next(self.parameters()).dtype) # fp16 compatibility
extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
# If a 2D ou 3D attention mask is provided for the cross-attention
# we need to make broadcastabe to [batch_size, num_heads, seq_length, seq_length]
if self.config.is_decoder and encoder_hidden_states is not None:
encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
if encoder_attention_mask is None:
encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)
if encoder_attention_mask.dim() == 3:
encoder_extended_attention_mask = encoder_attention_mask[:, None, :, :]
elif encoder_attention_mask.dim() == 2:
encoder_extended_attention_mask = encoder_attention_mask[:, None, None, :]
else:
raise ValueError(
"Wrong shape for encoder_hidden_shape (shape {}) or encoder_attention_mask (shape {})".format(
encoder_hidden_shape, encoder_attention_mask.shape
)
)
encoder_extended_attention_mask = encoder_extended_attention_mask.to(
dtype=next(self.parameters()).dtype
) # fp16 compatibility
encoder_extended_attention_mask = (1.0 - encoder_extended_attention_mask) * -10000.0
else:
encoder_extended_attention_mask = None
# Prepare head mask if needed
# 1.0 in head_mask indicate we keep the head
# attention_probs has shape bsz x n_heads x N x N
# input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
# and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
if head_mask is not None:
if head_mask.dim() == 1:
head_mask = head_mask.unsqueeze(0).unsqueeze(0).unsqueeze(-1).unsqueeze(-1)
head_mask = head_mask.expand(self.config.num_hidden_layers, -1, -1, -1, -1)
elif head_mask.dim() == 2:
head_mask = (
head_mask.unsqueeze(1).unsqueeze(-1).unsqueeze(-1)
) # We can specify head_mask for each layer
head_mask = head_mask.to(
dtype=next(self.parameters()).dtype
) # switch to fload if need + fp16 compatibility
else:
head_mask = [None] * self.config.num_hidden_layers
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,
)
sequence_output = encoder_outputs[0]
pooled_output = self.pooler(sequence_output)
outputs = (sequence_output, pooled_output,) + encoder_outputs[
1:
] # add hidden_states and attentions if they are here
return outputs # sequence_output, pooled_output, (hidden_states), (attentions).
上面是整個bert的代碼我們看看其中的一個部分
可以看到這裏只有一個encoder,也就是說 整個 bert只有一個encoder
encoder部分代碼
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 = ()
all_attentions = ()
for i, layer_module in enumerate(self.layer):
if self.output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_states,)
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)
很明顯,可以看到下圖這裏有對self.layer做一個for循環,也就是說這裏肯定有多lay_module的疊加,那我們先看self.layer是什麼
self.layer
self.layer是多個BertLayer,按照普通的conf.num_hidden_layers,是有23個BertLayer
BertLayer
class BertLayer(nn.Module):
def __init__(self, config):
super().__init__()
self.attention = BertAttention(config)
self.is_decoder = config.is_decoder
if self.is_decoder:
self.crossattention = BertAttention(config)
self.intermediate = BertIntermediate(config)
self.output = BertOutput(config)
def forward(
self,
hidden_states,
attention_mask=None,
head_mask=None,
encoder_hidden_states=None,
encoder_attention_mask=None,
):
self_attention_outputs = self.attention(hidden_states, attention_mask, head_mask)
attention_output = self_attention_outputs[0]
outputs = self_attention_outputs[1:] # add self attentions if we output attention weights
if self.is_decoder and encoder_hidden_states is not None:
cross_attention_outputs = self.crossattention(
attention_output, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask
)
attention_output = cross_attention_outputs[0]
outputs = outputs + cross_attention_outputs[1:] # add cross attentions if we output attention weights
intermediate_output = self.intermediate(attention_output)
layer_output = self.output(intermediate_output, attention_output)
outputs = (layer_output,) + outputs
return outputs
這裏就是個transformer結構了
總結
可以看出Bert包含了一個encoder,然後一個encoder結構裏有12個transformer.