add transformer seq encoder and add seq_feat in gf_view_finder

modules/seq_encoder/transformer_seq_encoder.py

@@ -1,10 +1,47 @@
+import torch
 from torch import nn
+
 import PytorchBoot.stereotype as stereotype
+import sys; sys.path.append(r"C:\Document\Local Project\nbv_rec\nbv_reconstruction")
+from modules.seq_encoder.abstract_seq_encoder import SequenceEncoder
 
 @stereotype.module("transformer_seq_encoder")
-class TransformerSequenceEncoder(nn.Module):
+class TransformerSequenceEncoder(SequenceEncoder):
     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, pose_embedding_list):
-        pass
+        combined_features = [torch.cat((pts_embed, pose_embed), dim=-1) for pts_embed, pose_embed in zip(pts_embedding_list[:-1], pose_embedding_list[:-1])]
+        combined_tensor = torch.stack(combined_features)
+        pos_encoding = self.positional_encoding[:, :combined_tensor.size(0), :]
+        combined_tensor = combined_tensor.unsqueeze(0) + pos_encoding
+        transformer_output = self.transformer_encoder(combined_tensor).squeeze(0)
+        final_feature = transformer_output.mean(dim=0)
+        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
+    pts_embedding_list = [torch.randn(config['pts_embed_dim']) for _ in range(seq_len)]
+    pose_embedding_list = [torch.randn(config['pose_embed_dim']) for _ in range(seq_len)]
+    output_feature = encoder.encode_sequence(pts_embedding_list, pose_embedding_list)
+    print("Encoded Feature:", output_feature)
+    print("Feature Shape:", output_feature.shape)