Spaces:
Running
Running
File size: 1,227 Bytes
426ffb5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 |
import torch.nn as nn
from .token import TokenEmbedding
from .position import PositionalEmbedding
class BERTEmbedding(nn.Module):
"""
BERT Embedding which is consisted with under features
1. TokenEmbedding : normal embedding matrix
2. PositionalEmbedding : adding positional information using sin, cos
2. SegmentEmbedding : adding sentence segment info, (sent_A:1, sent_B:2)
sum of all these features are output of BERTEmbedding
"""
def __init__(self, vocab_size, embed_size, max_len, dropout=0.1):
"""
:param vocab_size: total vocab size
:param embed_size: embedding size of token embedding
:param dropout: dropout rate
"""
super().__init__()
self.token = TokenEmbedding(vocab_size=vocab_size, embed_size=embed_size)
self.position = PositionalEmbedding(max_len=max_len, d_model=embed_size)
# self.segment = SegmentEmbedding(embed_size=self.token.embedding_dim)
self.dropout = nn.Dropout(p=dropout)
self.embed_size = embed_size
def forward(self, sequence):
x = self.token(sequence) # + self.position(sequence) # + self.segment(segment_label)
return self.dropout(x)
|