hofee/nbv_reconstruction
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

global_and_local: debug

Browse Source
This commit is contained in:
hofee 2024-10-29 17:12:24 +00:00
parent 830d51fc80
commit 26c3cb4c7a
3 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/server/server_train_config.yaml
View File

@ -106,7 +106,7 @@ module:
gf_view_finder:
t_feat_dim: 128
pose_feat_dim: 256
main_feat_dim: 2048
main_feat_dim: 2560
regression_head: Rx_Ry_and_T
pose_mode: rot_matrix
per_point_feature: False

5
core/nbv_dataset.py
View File

@ -34,7 +34,7 @@ class NBVReconstructionDataset(BaseDataset):
#self.model_dir = config["model_dir"]
self.filter_degree = config["filter_degree"]
if self.type == namespace.Mode.TRAIN:
scale_ratio = 100
scale_ratio = 50
self.datalist = self.datalist*scale_ratio
if self.cache:
expr_root = ConfigManager.get("runner", "experiment", "root_dir")
@ -206,9 +206,6 @@ class NBVReconstructionDataset(BaseDataset):
collate_data["combined_scanned_pts"] = torch.stack(
[torch.tensor(item["combined_scanned_pts"]) for item in batch]
)
collate_data["scanned_pts_mask"] = torch.stack(
[torch.tensor(item["scanned_pts_mask"]) for item in batch]
)
for key in batch[0].keys():
if key not in [

6
core/pipeline.py
View File

@ -20,8 +20,8 @@ class NBVReconstructionPipeline(nn.Module):
self.pose_encoder = ComponentFactory.create(
namespace.Stereotype.MODULE, self.module_config["pose_encoder"]
)
self.transformer_seq_encoder = ComponentFactory.create(
namespace.Stereotype.MODULE, self.module_config["transformer_seq_encoder"]
self.seq_encoder = ComponentFactory.create(
namespace.Stereotype.MODULE, self.module_config["seq_encoder"]
)
self.view_finder = ComponentFactory.create(
namespace.Stereotype.MODULE, self.module_config["view_finder"]
@ -112,7 +112,7 @@ class NBVReconstructionPipeline(nn.Module):
seq_embedding = torch.cat([pose_feat_seq, pts_feat_seq], dim=-1) # Tensor(S x (Dp+Dl))
embedding_list_batch.append(seq_embedding) # List(B): Tensor(S x (Dp+Dl))
seq_feat = self.transformer_seq_encoder.encode_sequence(embedding_list_batch) # Tensor(B x Ds)
seq_feat = self.seq_encoder.encode_sequence(embedding_list_batch) # Tensor(B x Ds)
main_feat = torch.cat([seq_feat, global_scanned_feat], dim=-1) # Tensor(B x (Ds+Dg))
if torch.isnan(main_feat).any():