63 lines
2.8 KiB
Python
63 lines
2.8 KiB
Python
import torch
|
|
from torch import nn
|
|
|
|
import PytorchBoot.stereotype as stereotype
|
|
|
|
@stereotype.module("transformer_seq_encoder")
|
|
class TransformerSequenceEncoder(nn.Module):
|
|
def __init__(self, config):
|
|
super(TransformerSequenceEncoder, self).__init__()
|
|
self.config = config
|
|
embed_dim = config['pts_embed_dim'] + config['pose_embed_dim']
|
|
self.positional_encoding = nn.Parameter(torch.zeros(1, config['max_seq_len'], embed_dim))
|
|
encoder_layer = nn.TransformerEncoderLayer(d_model=embed_dim, nhead=config['num_heads'], dim_feedforward=config['ffn_dim'])
|
|
self.transformer_encoder = nn.TransformerEncoder(encoder_layer, num_layers=config['num_layers'])
|
|
self.fc = nn.Linear(embed_dim, config['output_dim'])
|
|
|
|
def encode_sequence(self, pts_embedding_list_batch, pose_embedding_list_batch):
|
|
batch_size = len(pts_embedding_list_batch)
|
|
combined_features_batch = []
|
|
|
|
for i in range(batch_size):
|
|
combined_features = [torch.cat((pts_embed, pose_embed), dim=-1)
|
|
for pts_embed, pose_embed in zip(pts_embedding_list_batch[i][:-1], pose_embedding_list_batch[i][:-1])]
|
|
combined_features_batch.append(torch.stack(combined_features))
|
|
|
|
combined_tensor = torch.stack(combined_features_batch) # Shape: [batch_size, seq_len-1, embed_dim]
|
|
|
|
# Adjust positional encoding to match batch size
|
|
pos_encoding = self.positional_encoding[:, :combined_tensor.size(1), :].repeat(batch_size, 1, 1)
|
|
combined_tensor = combined_tensor + pos_encoding
|
|
|
|
# Transformer encoding
|
|
transformer_output = self.transformer_encoder(combined_tensor)
|
|
|
|
# Mean pooling
|
|
final_feature = transformer_output.mean(dim=1)
|
|
|
|
# Fully connected layer
|
|
final_output = self.fc(final_feature)
|
|
|
|
return final_output
|
|
|
|
if __name__ == "__main__":
|
|
config = {
|
|
'pts_embed_dim': 1024, # 每个点云embedding的维度
|
|
'pose_embed_dim': 256, # 每个姿态embedding的维度
|
|
'num_heads': 4, # 多头注意力机制的头数
|
|
'ffn_dim': 256, # 前馈神经网络的维度
|
|
'num_layers': 3, # Transformer 编码层数
|
|
'max_seq_len': 10, # 最大序列长度
|
|
'output_dim': 2048, # 输出特征维度
|
|
}
|
|
|
|
encoder = TransformerSequenceEncoder(config)
|
|
seq_len = 5
|
|
batch_size = 4
|
|
|
|
pts_embedding_list_batch = [torch.randn(seq_len, config['pts_embed_dim']) for _ in range(batch_size)]
|
|
pose_embedding_list_batch = [torch.randn(seq_len, config['pose_embed_dim']) for _ in range(batch_size)]
|
|
output_feature = encoder.encode_sequence(pts_embedding_list_batch, pose_embedding_list_batch)
|
|
print("Encoded Feature:", output_feature)
|
|
print("Feature Shape:", output_feature.shape)
|