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

update pbnbv

Browse Source
This commit is contained in:
hofee
2025-05-19 16:32:04 +08:00
parent b98753bfbb
commit cd436605a5
25 changed files with 1228 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
runners/global_points_inferencer.py
View File

@@ -34,6 +34,8 @@ class GlobalPointsInferencer(Runner):
self.min_new_area = ConfigManager.get(namespace.Stereotype.RUNNER, "min_new_area")
CM = 0.01
self.min_new_pts_num = self.min_new_area * (CM / self.voxel_size) **2
self.overlap_limit = ConfigManager.get(namespace.Stereotype.RUNNER, "overlap_limit")
self.enable_cluster = ConfigManager.get(namespace.Stereotype.RUNNER, "enable_cluster")
''' Pipeline '''
self.pipeline_name = self.config[namespace.Stereotype.PIPELINE]
self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
@@ -149,24 +151,12 @@ class GlobalPointsInferencer(Runner):
voxel_downsampled_combined_scanned_pts_np, inverse = self.voxel_downsample_with_mapping(combined_scanned_pts, voxel_threshold)
output = self.pipeline(input_data)
pred_pose_9d = output["pred_pose_9d"]
if not self.enable_cluster:
pred_pose_9d_candidates = [pred_pose_9d[0]]
else:
predict_result = PredictResult(pred_pose_9d.cpu().numpy(), input_pts=input_data["combined_scanned_pts"][0].cpu().numpy(), cluster_params=dict(eps=0.25, min_samples=3))
pred_pose_9d_candidates = predict_result.candidate_9d_poses
pred_pose = torch.eye(4, device=pred_pose_9d.device)
# # save pred_pose_9d ------
# root = "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/temp_output_result"
# scene_dir = os.path.join(root, scene_name)
# if not os.path.exists(scene_dir):
# os.makedirs(scene_dir)
# pred_9d_path = os.path.join(scene_dir,f"pred_pose_9d_{len(pred_cr_seq)}.npy")
# pts_path = os.path.join(scene_dir,f"combined_scanned_pts_{len(pred_cr_seq)}.txt")
# np_combined_scanned_pts = input_data["combined_scanned_pts"][0].cpu().numpy()
# np.save(pred_9d_path, pred_pose_9d.cpu().numpy())
# np.savetxt(pts_path, np_combined_scanned_pts)
# # ----- ----- -----
predict_result = PredictResult(pred_pose_9d.cpu().numpy(), input_pts=input_data["combined_scanned_pts"][0].cpu().numpy(), cluster_params=dict(eps=0.25, min_samples=3))
# -----------------------
# import ipdb; ipdb.set_trace()
# predict_result.visualize()
# -----------------------
pred_pose_9d_candidates = predict_result.candidate_9d_poses
for pred_pose_9d in pred_pose_9d_candidates:
#import ipdb; ipdb.set_trace()
pred_pose_9d = torch.tensor(pred_pose_9d, dtype=torch.float32).to(self.device).unsqueeze(0)
@@ -181,12 +171,13 @@ class GlobalPointsInferencer(Runner):
curr_overlap_area_threshold = overlap_area_threshold * 0.5
downsampled_new_target_pts = PtsUtil.voxel_downsample_point_cloud(new_target_pts, voxel_threshold)
overlap, _ = ReconstructionUtil.check_overlap(downsampled_new_target_pts, voxel_downsampled_combined_scanned_pts_np, overlap_area_threshold = curr_overlap_area_threshold, voxel_size=voxel_threshold, require_new_added_pts_num = True)
if not overlap:
Log.yellow("no overlap!")
retry += 1
retry_overlap_pose.append(pred_pose.cpu().numpy().tolist())
continue
if self.overlap_limit:
overlap, _ = ReconstructionUtil.check_overlap(downsampled_new_target_pts, voxel_downsampled_combined_scanned_pts_np, overlap_area_threshold = curr_overlap_area_threshold, voxel_size=voxel_threshold, require_new_added_pts_num = True)
if not overlap:
Log.yellow("no overlap!")
retry += 1
retry_overlap_pose.append(pred_pose.cpu().numpy().tolist())
continue
history_indices.append(new_scan_points_indices)
except Exception as e: