After long running of Aachen.pipeline, It panicked for not found pycolmap._core.Camera.model_id

[ddwolf]

Version: Hierarchical-Localization-1.4

Ubuntu 24.10

Python 3.12.7

Command: python3 -m hloc.pipelines.Aachen.pipeline

Configs for feature extractors:
{'cosplace': {'model': {'name': 'cosplace'},
              'output': 'global-feats-cosplace',
              'preprocessing': {'resize_max': 1024}},
 'd2net-ss': {'model': {'multiscale': False, 'name': 'd2net'},
              'output': 'feats-d2net-ss',
              'preprocessing': {'grayscale': False, 'resize_max': 1600}},
 'dir': {'model': {'name': 'dir'},
         'output': 'global-feats-dir',
         'preprocessing': {'resize_max': 1024}},
 'disk': {'model': {'max_keypoints': 5000, 'name': 'disk'},
          'output': 'feats-disk',
          'preprocessing': {'grayscale': False, 'resize_max': 1600}},
 'netvlad': {'model': {'name': 'netvlad'},
             'output': 'global-feats-netvlad',
             'preprocessing': {'resize_max': 1024}},
 'openibl': {'model': {'name': 'openibl'},
             'output': 'global-feats-openibl',
             'preprocessing': {'resize_max': 1024}},
 'r2d2': {'model': {'max_keypoints': 5000, 'name': 'r2d2'},
          'output': 'feats-r2d2-n5000-r1024',
          'preprocessing': {'grayscale': False, 'resize_max': 1024}},
 'sift': {'model': {'name': 'dog'},
          'output': 'feats-sift',
          'preprocessing': {'grayscale': True, 'resize_max': 1600}},
 'sosnet': {'model': {'descriptor': 'sosnet', 'name': 'dog'},
            'output': 'feats-sosnet',
            'preprocessing': {'grayscale': True, 'resize_max': 1600}},
 'superpoint_aachen': {'model': {'max_keypoints': 4096,
                                 'name': 'superpoint',
                                 'nms_radius': 3},
                       'output': 'feats-superpoint-n4096-r1024',
                       'preprocessing': {'grayscale': True,
                                         'resize_max': 1024}},
 'superpoint_inloc': {'model': {'max_keypoints': 4096,
                                'name': 'superpoint',
                                'nms_radius': 4},
                      'output': 'feats-superpoint-n4096-r1600',
                      'preprocessing': {'grayscale': True, 'resize_max': 1600}},
 'superpoint_max': {'model': {'max_keypoints': 4096,
                              'name': 'superpoint',
                              'nms_radius': 3},
                    'output': 'feats-superpoint-n4096-rmax1600',
                    'preprocessing': {'grayscale': True,
                                      'resize_force': True,
                                      'resize_max': 1600}}}
Configs for feature matchers:
{'NN-mutual': {'model': {'do_mutual_check': True, 'name': 'nearest_neighbor'},
               'output': 'matches-NN-mutual'},
 'NN-ratio': {'model': {'do_mutual_check': True,
                        'name': 'nearest_neighbor',
                        'ratio_threshold': 0.8},
              'output': 'matches-NN-mutual-ratio.8'},
 'NN-superpoint': {'model': {'distance_threshold': 0.7,
                             'do_mutual_check': True,
                             'name': 'nearest_neighbor'},
                   'output': 'matches-NN-mutual-dist.7'},
 'adalam': {'model': {'name': 'adalam'}, 'output': 'matches-adalam'},
 'disk+lightglue': {'model': {'features': 'disk', 'name': 'lightglue'},
                    'output': 'matches-disk-lightglue'},
 'superglue': {'model': {'name': 'superglue',
                         'sinkhorn_iterations': 50,
                         'weights': 'outdoor'},
               'output': 'matches-superglue'},
 'superglue-fast': {'model': {'name': 'superglue',
                              'sinkhorn_iterations': 5,
                              'weights': 'outdoor'},
                    'output': 'matches-superglue-it5'},
 'superpoint+lightglue': {'model': {'features': 'superpoint',
                                    'name': 'lightglue'},
                          'output': 'matches-superpoint-lightglue'}}
[2025/01/16 03:01:18 hloc INFO] Extracting local features with configuration:
{'model': {'max_keypoints': 4096, 'name': 'superpoint', 'nms_radius': 3},
 'output': 'feats-superpoint-n4096-r1024',
 'preprocessing': {'grayscale': True, 'resize_max': 1024}}
[2025/01/16 03:01:18 hloc INFO] Found 5426 images in root datasets/aachen/images_upright.
[2025/01/16 03:01:20 hloc INFO] Skipping the extraction.
[2025/01/16 03:01:20 hloc INFO] Found 13026 images and 13026 cameras in database.
[2025/01/16 03:01:20 hloc INFO] Reading the NVM model...
[2025/01/16 03:01:20 hloc INFO] Reading 4328 cameras...
[2025/01/16 03:01:20 hloc INFO] Reading 4328 images...
[2025/01/16 03:01:20 hloc INFO] Reading 1652687 points...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 1652687/1652687 [00:24<00:00, 68819.92pts/s]
[2025/01/16 03:01:44 hloc INFO] Parsing image data...
[2025/01/16 03:02:04 hloc INFO] Writing the COLMAP model...
[2025/01/16 03:03:24 hloc INFO] Done.
[2025/01/16 03:03:25 hloc INFO] Reading the COLMAP model...
[2025/01/16 03:03:53 hloc INFO] Extracting image pairs from covisibility info...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4328/4328 [00:47<00:00, 90.50it/s]
[2025/01/16 03:04:41 hloc INFO] Found 85515 pairs.
[2025/01/16 03:04:42 hloc INFO] Matching local features with configuration:
{'model': {'name': 'superglue',
           'sinkhorn_iterations': 50,
           'weights': 'outdoor'},
 'output': 'matches-superglue'}
/home/benchmark/repos/Hierarchical-Localization-1.4/SuperGluePretrainedNetwork/models/superglue.py:226: FutureWarning: You are using `torch.load` with `weights_only=F
uct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more 
he functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted b
r any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  self.load_state_dict(torch.load(str(path)))
Loaded SuperGlue model ("outdoor" weights)
  1%|█▌                                                                                                              | 809/56479 [38:19<52:35:26,  3.40s/it] 55%|█████
2/56479 [24:26:13<21:55:55,  3.08s/it]
 61%|█████████████████████████████████████████████████████████████████                                          | 34343/56479 [27:13:10<14:17:28,  2.32s/it]100%|█████
6479/56479 [44:35:59<00:00,  2.84s/it]
[2025/01/17 23:40:43 hloc INFO] Finished exporting matches.

Error:

100% ████████████████████████████████████████████| 56479/56479 [44:35:59<00:00,  2.84s/it]
[2025/01/17 23:40:43 hloc INFO] Finished exporting matches.
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/home/benchmark/repos/Hierarchical-Localization-1.4/hloc/pipelines/Aachen/pipeline.py", line 53, in <module>
    triangulation.main(
  File "/home/benchmark/repos/Hierarchical-Localization-1.4/hloc/triangulation.py", line 222, in main
    image_ids = create_db_from_model(reference, database)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/benchmark/repos/Hierarchical-Localization-1.4/hloc/triangulation.py", line 46, in create_db_from_model
    camera.model_id, camera.width, camera.height, camera.params,
    ^^^^^^^^^^^^^^^
AttributeError: 'pycolmap._core.Camera' object has no attribute 'model_id'