def forward(self, sequences_batch, sequences_lengths):
"""
Args:
sequences_batch: A batch of variable length sequences of vectors.
The batch is assumed to be of size
(batch, sequence, vector_dim).
sequences_lengths: A 1D tensor containing the sizes of the
sequences in the input batch.
Returns:
reordered_outputs: The outputs (hidden states) of the encoder for
the sequences in the input batch, in the same order.
"""
sorted_batch, sorted_lengths, _, restoration_idx =\
sort_by_seq_lens(sequences_batch, sequences_lengths)
packed_batch = nn.utils.rnn.pack_padded_sequence(sorted_batch,
sorted_lengths,
batch_first=True)
outputs, _ = self._encoder(packed_batch, None)
outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs,
batch_first=True)
reordered_outputs = outputs.index_select(0, restoration_idx)
return reordered_outputs
def forward(self, sequence_batch, sequence_lengths):
sorted_batch, sorted_seq_lens, _, restoration_index = sort_by_seq_lens(
sequence_batch, sequence_lengths)
packed_batch = nn.utils.rnn.pack_padded_sequence(sorted_batch,
sorted_seq_lens,
batch_first=True)
output, _ = self.encoder(packed_batch)
output, _ = nn.utils.rnn.pad_packed_sequence(output, batch_first=True)
return output.index_select(0, restoration_index)
def forward(self, sequences_batch, sequnces_lengths):
# 用于处理 padding token
max_len = sequences_batch.shape[1]
sorted_batch, sorted_length, _, restoration_idx = sort_by_seq_lens(sequences_batch, sequnces_lengths) #长度排序
packed_batch = nn.utils.rnn.pack_padded_sequence(sorted_batch, sorted_length, batch_first=True) #压缩
outputs, _ = self._encoder(packed_batch) # LSTM
outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs, batch_first=True, total_length=max_len) #还原 [batch_size, max_len, dim]
# restore order
reorder_outputs = outputs.index_select(0, restoration_idx) #还原顺序
return reorder_outputs
def forward(self, sequences_batch, sequences_lengths):
# 对batch中的序列进行排序，得到排序后的batch和恢复序列
sorted_batch, sorted_lengths, _, restoration_idx = sort_by_seq_lens(sequences_batch, sequences_lengths) # 排序
packed_batch = nn.utils.rnn.pack_padded_sequence(sorted_batch, sorted_lengths, batch_first=True) # pack
outputs, _ = self.encoder(packed_batch, None) # LSTM 运算
outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs, batch_first=True) # pad数据，恢复成padding等长的结构
# for linux
# 恢复其索引序列（先前不是排序了嘛，现在需要恢复回去）
reordered_outputs = outputs.index_select(0, restoration_idx)
"""
for win10
reordered_outputs = outputs.index_select(0, restoration_idx.long())
"""
return reordered_outputs
def forward(self, sequences_batch, sequences_lengths):
sorted_batch, sorted_lengths, _, restoration_idx = sort_by_seq_lens(
sequences_batch, sequences_lengths)
packed_batch = nn.utils.rnn.pack_padded_sequence(sorted_batch,
sorted_lengths,
batch_first=True)
outputs, _ = self.encoder(packed_batch, None)
outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs,
batch_first=True)
# for linux
if platform == "linux" or platform == "linux2":
reordered_outputs = outputs.index_select(0, restoration_idx)
# for win10
else:
reordered_outputs = outputs.index_select(0, restoration_idx.long())
return reordered_outputs