problem: KeyError: ['track_id'] #24
Description
I only modified the video example_dancetrack0058.mp4, edited it. Then I didn't modify any other configuration files, I used tracklab -cn cameltrack on the command line, and then I got an error:
(cameltrack) PS E:\vscode\qq\creak\CAMELTrack> tracklab -cn cameltrack
[07/28/25 16:04:11] INFO Run directory: main.py:103
E:\vscode\qq\creak\CAMELTrack\outputs\CAMELTrack\2025-07-28\16-04-11
INFO Using device: 'cuda'. main.py:104
[07/28/25 16:04:15] INFO ExternalVideo= val set: 1 main.py:32
Overwriting current config with config loaded from E:\vscode\qq\creak\CAMELTrack/pretrained_models/reid/kpr_dancetrack_sportsmot_posetrack21_occludedduke_market_split0.pth.tar
WARNING: the train dataset of the loaded model is different from the target dataset in the current config.
Successfully loaded pretrained weights from "E:\vscode\qq\creak\CAMELTrack/pretrained_models/reid/kpr_dancetrack_sportsmot_posetrack21_occludedduke_market_split0.pth.tar"
[07/28/25 16:04:19] INFO Loading CAMEL checkpoint from cameltrack.py:96
E:\vscode\qq\creak\CAMELTrack\pretrained_models\camel\camel_bbox_app_ kps_global.ckpt.
INFO Pipeline: YOLOUltralyticsPose -> KPReId -> CAMELTrack module.py:67
INFO Starting tracking operation on val set. main.py:50
INFO Saving TrackerState to tracker_state.py:52
E:\vscode\qq\creak\CAMELTrack\states\CAMELTrack-val.pklz
INFO Pipeline has been validated module.py:84
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1 0:02:23 • -:--:--
KPReId ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1350 0:01:09 • -:--:--D:\a\envs\cameltrack\Lib\site-packages\tracklab\utils\collate.py:27: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
storage = elem.storage()._new_shared(numel)
D:\a\envs\cameltrack\Lib\site-packages\tracklab\utils\collate.py:27: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
storage = elem.storage()._new_shared(numel)
D:\a\envs\cameltrack\Lib\site-packages\tracklab\utils\collate.py:27: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storD:\a\envs\cameltrack\Lib\site-packages\tracklab\utils\collate.py:27: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storl be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storare using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
age()
storage = elem.storage()._new_shared(numel)
D:\a\envs\cameltrack\Lib\site-packages\tracklab\utils\collate.py:27: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1 0:02:23 • -:--:--
KPReId ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1350 0:01:09 • -:--:--D:\a\envs\cameltrack\Lib\site-packages\tracklab\utils\collate.py:27: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1 0:05:02 • -:--:--
CAMELTrack ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/9 0:01:09 • -:--:--E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_height"] = torch.tensor(image.shape[0])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_height"] = torch.tensor(image.shape[0])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_height"] = torch.tensor(image.shape[0])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1 0:05:02 • -:--:--
CAMELTrack ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/9 0:01:09 • -:--:--E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_height"] = torch.tensor(image.shape[0])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_height"] = torch.tensor(image.shape[0])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_height"] = torch.tensor(image.shape[0])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/1 0:05:02 • -:--:--
CAMELTrack ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/9 0:01:09 • -:--:--E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:136: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
detections["im_width"] = torch.tensor(image.shape[1])
E:\vscode\qq\creak\CAMELTrack\cameltrack\cameltrack.py:137: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1 0:05:05 • 0:00:00
Visualization ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/9 0:00:11 • -:--:--Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'tTracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1 0:05:05 • 0:00:00
Visualization ━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/9 0:00:11 • -:--:--Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'tTracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1 0:05:05 • 0:00:00
Visualization ━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/9 0:00:11 • -:--:--Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'tTracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1 0:05:05 • 0:00:00
Visualization ━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/9 0:00:11 • -:--:--Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 'track_id' during drawing.
Visualizer <class 'tracklab.visualization.visualizer.Visualizer'> raised error : 'Series' object has no attribute 't[07/28/25 16:09:37] INFO 0 already exists in tracker_state.py:320
E:\vscode\qq\creak\CAMELTrack\states\CAMELTrack-val.pklz file
Tracking videos (2) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1 0:05:05 • 0:00:00
INFO Visualization output at : visualization_engine.py:52
E:\vscode\qq\creak\CAMELTrack\outputs\CAMELTrack\2025-07-28\
16-04-11\visualization
INFO Tracking ended, final TrackerState stats: tracker_state.py:262
INFO Total # detections: 2700 (GT=0) tracker_state.py:378
INFO Total # detections with track_id: tracker_state.py:387
INFO Total # track_ids: tracker_state.py:388
INFO Starting evaluation. main.py:117
INFO Starting evaluation using TrackEval library trackeval_evaluator.py:29
(https://github.com/JonathonLuiten/TrackEval)
Error executing job with overrides: []
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in run_code
File "D:\a\envs\cameltrack\Scripts\tracklab.exe_main.py", line 7, in
File "D:\a\envs\cameltrack\Lib\site-packages\hydra\main.py", line 94, in decorated_main
_run_hydra(
File "D:\a\envs\cameltrack\Lib\site-packages\hydra_internal\utils.py", line 394, in _run_hydra
_run_app(
File "D:\a\envs\cameltrack\Lib\site-packages\hydra_internal\utils.py", line 457, in _run_app
run_and_report(
File "D:\a\envs\cameltrack\Lib\site-packages\hydra_internal\utils.py", line 223, in run_and_report
raise ex
File "D:\a\envs\cameltrack\Lib\site-packages\hydra_internal\utils.py", line 220, in run_and_report
return func()
^^^^^^
File "D:\a\envs\cameltrack\Lib\site-packages\hydra_internal\utils.py", line 458, in
lambda: hydra.run(
^^^^^^^^^^
File "D:\a\envs\cameltrack\Lib\site-packages\hydra_internal\hydra.py", line 132, in run
_ = ret.return_value
^^^^^^^^^^^^^^^^
File "D:\a\envs\cameltrack\Lib\site-packages\hydra\core\utils.py", line 260, in return_value
raise self._return_value
File "D:\a\envs\cameltrack\Lib\site-packages\hydra\core\utils.py", line 186, in run_job
ret.return_value = task_function(task_cfg)
^^^^^^^^^^^^^^^^^^^^^^^
File "D:\a\envs\cameltrack\Lib\site-packages\tracklab\main.py", line 65, in main
evaluate(cfg, evaluator, tracker_state)
File "D:\a\envs\cameltrack\Lib\site-packages\tracklab\main.py", line 118, in evaluate
evaluator.run(tracker_state)
File "D:\a\envs\cameltrack\Lib\site-packages\tracklab\wrappers\eval\trackeval_evaluator.py", line 36, in run
self.tracking_dataset.save_for_eval(
File "D:\a\envs\cameltrack\Lib\site-packages\tracklab\datastruct\tracking_dataset.py", line 207, in save_for_eval
mot_df = self._mot_encoding(detections, image_metadatas, video_metadatas, bbox_column_for_eval)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\a\envs\cameltrack\Lib\site-packages\tracklab\datastruct\tracking_dataset.py", line 173, in _mot_encoding
df.dropna(
File "D:\a\envs\cameltrack\Lib\site-packages\pandas\core\frame.py", line 6677, in dropna
raise KeyError(np.array(subset)[check].tolist())
KeyError: ['track_id']
[W728 16:09:38.000000000 CudaIPCTypes.cpp:96] Producer process tried to deallocate over 1000 memory blocks referred by consumer processes. Deallocation might be significantly slowed down. We assume it will never going to be the case, but if it is, please file but to https://github.com/pytorch/pytorch
[W728 16:09:38.000000000 CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
cameltrack.yaml:
Please help me