solve merge

configs/local/inference_config.yaml

@@ -70,7 +70,7 @@ module:
     global_feat: True
     feature_transform: False
   transformer_seq_encoder:
-    embed_dim: 256
+    embed_dim: 320
     num_heads: 4
     ffn_dim: 256
     num_layers: 3

core/pipeline.py

@@ -90,6 +90,7 @@ class NBVReconstructionPipeline(nn.Module):
         scanned_n_to_world_pose_9d_batch = data[
             "scanned_n_to_world_pose_9d"
         ]  # List(B): Tensor(S x 9)
+        scanned_pts_mask_batch = data["scanned_pts_mask"] # List(B): Tensor(S x N)
 
         scanned_pts_mask_batch = data["scanned_pts_mask"] # List(B): Tensor(N)
 
@@ -136,4 +137,4 @@ class NBVReconstructionPipeline(nn.Module):
                     ipdb.set_trace()
             Log.error("nan in main_feat", True)
 
-        return main_feat
+        return main_feat

runners/inferencer.py

@@ -92,7 +92,8 @@ class Inferencer(Runner):
                         output = self.predict_sequence(data)
                         self.save_inference_result(test_set_name, data["scene_name"], output)
                     except Exception as e:
-                        Log.error(f"Error in scene {scene_name}, {e}")
+                        print(e)
+                        Log.error(f"Error, {e}")
                         continue
                     
             status_manager.set_progress("inference", "inferencer", f"dataset", len(self.test_set_list), len(self.test_set_list))
@@ -116,7 +117,9 @@ class Inferencer(Runner):
         
         ''' data for inference '''
         input_data = {}
+        
         input_data["combined_scanned_pts"] = torch.tensor(data["first_scanned_pts"][0], dtype=torch.float32).to(self.device).unsqueeze(0)
+        input_data["scanned_pts_mask"] = [torch.zeros(input_data["combined_scanned_pts"].shape[1], dtype=torch.bool).to(self.device).unsqueeze(0)]
         input_data["scanned_n_to_world_pose_9d"] = [torch.tensor(data["first_scanned_n_to_world_pose_9d"], dtype=torch.float32).to(self.device)]
         input_data["mode"] = namespace.Mode.TEST
         input_pts_N = input_data["combined_scanned_pts"].shape[1]
@@ -254,6 +257,14 @@ class Inferencer(Runner):
 
         return result
 
+    def voxel_downsample_with_mapping(self, point_cloud, voxel_size=0.003):
+        voxel_indices = np.floor(point_cloud / voxel_size).astype(np.int32)
+        unique_voxels, inverse, counts = np.unique(voxel_indices, axis=0, return_inverse=True, return_counts=True)
+        idx_sort = np.argsort(inverse)
+        idx_unique = idx_sort[np.cumsum(counts)-counts]
+        downsampled_points = point_cloud[idx_unique]
+        return downsampled_points, inverse
+    
     def compute_coverage_rate(self, scanned_view_pts, new_pts, model_pts, threshold=0.005):
         if new_pts is not None:
             new_scanned_view_pts = scanned_view_pts + [new_pts]