global: upd inference

configs/local/inference_config.yaml

@@ -6,71 +6,67 @@ runner:
     cuda_visible_devices: "0,1,2,3,4,5,6,7"
     
   experiment:
-    name: w_gf_wo_lf_full
+    name: overfit_ab_global_only
     root_dir: "experiments"
-    epoch: 1 # -1 stands for last epoch
+    epoch: -1 # -1 stands for last epoch
 
   test:
     dataset_list:
       - OmniObject3d_train
 
-  blender_script_path: "/media/hofee/data/project/python/nbv_reconstruction/blender/data_renderer.py"
+  blender_script_path: "/data/hofee/project/nbv_rec/blender/data_renderer.py"
-  output_dir: "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/test/inference_global_full_on_testset"
+  output_dir: "/data/hofee/data/inference_global_full_on_testset"
-  pipeline: nbv_reconstruction_global_pts_pipeline
+  pipeline: nbv_reconstruction_pipeline
+  voxel_size: 0.003
   
 dataset:
   OmniObject3d_train:
-    root_dir: "/media/hofee/repository/nbv_reconstruction_data_512"
+    root_dir: "/data/hofee/data/new_full_data"
-    model_dir: "/media/hofee/data/data/scaled_object_meshes"
+    model_dir: "/data/hofee/data/scaled_object_meshes"
-    source: seq_nbv_reconstruction_dataset
+    source: seq_reconstruction_dataset
-    split_file: "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/test/test_set_list.txt"
+    split_file: "/data/hofee/data/sample.txt"
     type: test
     filter_degree: 75
     ratio: 1
     batch_size: 1
     num_workers: 12
-    pts_num: 4096
+    pts_num: 8192
-    load_from_preprocess: False
+    load_from_preprocess: True
+
+  OmniObject3d_test:
+    root_dir: "/data/hofee/data/new_full_data"
+    model_dir: "/data/hofee/data/scaled_object_meshes"
+    source: seq_reconstruction_dataset
+    split_file: "/data/hofee/data/sample.txt"
+    type: test
+    filter_degree: 75
+    eval_list:
+      - pose_diff
+      - coverage_rate_increase
+    ratio: 0.1
+    batch_size: 1
+    num_workers: 12
+    pts_num: 8192
+    load_from_preprocess: True
 
 pipeline:
-  nbv_reconstruction_local_pts_pipeline:
+  nbv_reconstruction_pipeline:
     modules:
       pts_encoder: pointnet_encoder
       seq_encoder: transformer_seq_encoder
       pose_encoder: pose_encoder
       view_finder: gf_view_finder
     eps: 1e-5
-    global_scanned_feat: False
-
-  nbv_reconstruction_global_pts_pipeline:
-    modules:
-      pts_encoder: pointnet_encoder
-      pose_seq_encoder: transformer_pose_seq_encoder
-      pose_encoder: pose_encoder
-      view_finder: gf_view_finder
-    eps: 1e-5
     global_scanned_feat: True
 
-
-    
 module:
-
   pointnet_encoder:
     in_dim: 3
     out_dim: 1024
     global_feat: True
     feature_transform: False
-
   transformer_seq_encoder:
-    pts_embed_dim: 1024
+    embed_dim: 256
-    pose_embed_dim: 256
-    num_heads: 4
-    ffn_dim: 256
-    num_layers: 3
-    output_dim: 2048
-
-  transformer_pose_seq_encoder:
-    pose_embed_dim: 256
     num_heads: 4
     ffn_dim: 256
     num_layers: 3
@@ -86,7 +82,8 @@ module:
     sample_mode: ode
     sampling_steps: 500
     sde_mode: ve
-
   pose_encoder:
     pose_dim: 9
     out_dim: 256
+  pts_num_encoder:
+    out_dim: 64

core/seq_dataset.py

@@ -103,6 +103,18 @@ class SeqReconstructionDataset(BaseDataset):
         except Exception as e:
             Log.error(f"Save cache failed: {e}")
 
+    def seq_combined_pts(self, scene, frame_idx_list):
+        all_combined_pts = []   
+        for i in frame_idx_list:
+            path = DataLoadUtil.get_path(self.root_dir, scene, i)
+            pts = DataLoadUtil.load_from_preprocessed_pts(path,"npy")
+            if pts.shape[0] == 0:
+                continue
+            all_combined_pts.append(pts)
+        all_combined_pts = np.vstack(all_combined_pts)
+        downsampled_all_pts = PtsUtil.voxel_downsample_point_cloud(all_combined_pts, 0.003)
+        return downsampled_all_pts
+
     def __getitem__(self, index):
         data_item_info = self.datalist[index]
         max_coverage_rate = data_item_info["max_coverage_rate"]
@@ -130,20 +142,26 @@ class SeqReconstructionDataset(BaseDataset):
         n_to_world_6d = PoseUtil.matrix_to_rotation_6d_numpy(
             np.asarray(n_to_world_pose[:3, :3])
         ) 
+        first_left_cam_pose = cam_info["cam_to_world"]
+        first_center_cam_pose = cam_info["cam_to_world_O"]
+        first_O_to_first_L_pose = np.dot(np.linalg.inv(first_left_cam_pose), first_center_cam_pose)
         n_to_world_trans = n_to_world_pose[:3, 3]
         n_to_world_9d = np.concatenate([n_to_world_6d, n_to_world_trans], axis=0)
         scanned_n_to_world_pose.append(n_to_world_9d)
 
-        # combined_scanned_views_pts = np.concatenate(scanned_views_pts, axis=0)
+        frame_list = []
-        # voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_views_pts, 0.002)
+        for i in range(DataLoadUtil.get_scene_seq_length(self.root_dir, scene_name)):
-        # random_downsampled_combined_scanned_pts_np = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, self.pts_num)
+            frame_list.append(i)
-        
+        gt_pts = self.seq_combined_pts(scene_name, frame_list)
         data_item = {
             "first_scanned_pts": np.asarray(scanned_views_pts, dtype=np.float32), # Ndarray(S x Nv x 3)
             "first_scanned_coverage_rate": scanned_coverages_rate, # List(S): Float, range(0, 1)
             "first_scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9)
             "seq_max_coverage_rate": max_coverage_rate, # Float, range(0, 1)
             "scene_name": scene_name, # String
+            "gt_pts": gt_pts, # Ndarray(N x 3)
+            "scene_path": os.path.join(self.root_dir, scene_name), # String
+            "O_to_L_pose": first_O_to_first_L_pose,
         }
 
         return data_item

runners/inferencer.py

@@ -27,6 +27,7 @@ class Inferencer(Runner):
     
         self.script_path = ConfigManager.get(namespace.Stereotype.RUNNER, "blender_script_path")
         self.output_dir = ConfigManager.get(namespace.Stereotype.RUNNER, "output_dir")
+        self.voxel_size = ConfigManager.get(namespace.Stereotype.RUNNER, "voxel_size")
         ''' Pipeline '''
         self.pipeline_name = self.config[namespace.Stereotype.PIPELINE]
         self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
@@ -65,16 +66,11 @@ class Inferencer(Runner):
             for dataset_idx, test_set in enumerate(self.test_set_list):
                 status_manager.set_progress("inference", "inferencer", f"dataset", dataset_idx, len(self.test_set_list))
                 test_set_name = test_set.get_name()
-                test_loader = test_set.get_loader()
 
-                if test_loader.batch_size > 1:
+                total=int(len(test_set))
-                    Log.error("Batch size should be 1 for inference, found {} in {}".format(test_loader.batch_size, test_set_name), terminate=True)
+                for i in range(total):
-
+                    data = test_set.__getitem__(i)
-                total=int(len(test_loader))
-                loop = tqdm(enumerate(test_loader), total=total)
-                for i, data in loop:
                     status_manager.set_progress("inference", "inferencer", f"Batch[{test_set_name}]", i+1, total)
-                    test_set.process_batch(data, self.device)
                     output = self.predict_sequence(data)
                     self.save_inference_result(test_set_name, data["scene_name"][0], output)
                     
@@ -88,26 +84,23 @@ class Inferencer(Runner):
         ''' data for rendering '''
         scene_path = data["scene_path"][0]
         O_to_L_pose = data["O_to_L_pose"][0]
-        voxel_threshold = data["voxel_threshold"][0]
+        voxel_threshold = self.voxel_size
-        filter_degree = data["filter_degree"][0]
+        filter_degree = 75
-        model_points_normals = data["model_points_normals"][0]
+        down_sampled_model_pts = data["gt_pts"]
-        model_pts = model_points_normals[:,:3]
+        import ipdb; ipdb.set_trace()
-        down_sampled_model_pts = PtsUtil.voxel_downsample_point_cloud(model_pts, voxel_threshold)
+        first_frame_to_world_9d = data["first_scanned_n_to_world_pose_9d"][0]
-        first_frame_to_world_9d = data["first_to_world_9d"][0]
+        first_frame_to_world = np.eye(4)
-        first_frame_to_world = torch.eye(4, device=first_frame_to_world_9d.device)
+        first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_numpy(first_frame_to_world_9d[:6])
-        first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_tensor_batch(first_frame_to_world_9d[:,:6])[0]
+        first_frame_to_world[:3,3] = first_frame_to_world_9d[6:]
-        first_frame_to_world[:3,3] = first_frame_to_world_9d[0,6:]
-        first_frame_to_world = first_frame_to_world.to(self.device)
         
         ''' data for inference '''
         input_data = {}
-        input_data["scanned_pts"] = [data["first_pts"][0].to(self.device)]
+        input_data["combined_scanned_pts"] = torch.tensor(data["first_scanned_pts"][0], dtype=torch.float32).to(self.device)
-        input_data["scanned_n_to_world_pose_9d"] = [data["first_to_world_9d"][0].to(self.device)]
+        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_data["combined_scanned_pts"] = data["combined_scanned_pts"]
+        input_pts_N = input_data["combined_scanned_pts"].shape[1]
-        input_pts_N = input_data["scanned_pts"][0].shape[1]
         
-        first_frame_target_pts, _ = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, model_points_normals, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
+        first_frame_target_pts, _ = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, down_sampled_model_pts, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
         scanned_view_pts = [first_frame_target_pts]
         last_pred_cr = self.compute_coverage_rate(scanned_view_pts, None, down_sampled_model_pts, threshold=voxel_threshold)
 

utils/render.py

@@ -10,7 +10,7 @@ from utils.pts import PtsUtil
 class RenderUtil:
 
     @staticmethod
-    def render_pts(cam_pose, scene_path, script_path, model_points_normals, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
+    def render_pts(cam_pose, scene_path, script_path, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
         
         nO_to_world_pose = DataLoadUtil.get_real_cam_O_from_cam_L(cam_pose, nO_to_nL_pose, scene_path=scene_path)
 
@@ -34,10 +34,10 @@ class RenderUtil:
                 return None
             path = os.path.join(temp_dir, "tmp")
             point_cloud = DataLoadUtil.get_target_point_cloud_world_from_path(path, binocular=True)
+            normals = DataLoadUtil.get_target_normals_world_from_path(path, binocular=True)
             cam_params = DataLoadUtil.load_cam_info(path, binocular=True)
             
-            ''' TODO: old code: filter_points api is changed, need to update the code '''
+            filtered_point_cloud = PtsUtil.filter_points(point_cloud, normals, cam_pose=cam_params["cam_to_world"], voxel_size=voxel_threshold, theta=filter_degree)
-            filtered_point_cloud = PtsUtil.filter_points(point_cloud, model_points_normals, cam_pose=cam_params["cam_to_world"], voxel_size=voxel_threshold, theta=filter_degree)
             full_scene_point_cloud = None
             if require_full_scene:
                 depth_L, depth_R = DataLoadUtil.load_depth(path, cam_params['near_plane'], cam_params['far_plane'], binocular=True)