Errors occurring during testing

[SherLockLi99]

Hello! When I enter the command to test, the following error occurs, what should I do to solve the following problem [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 6020/6019, 19.2 task/s, elapsed: 313s, ETA: 0s truncate 6019 samples from 6019 start evaluation! len of the results 6019 saving submissions results to ./work_dirs/nusc_baseline_480_60x30_30e/submission_vector.json collected 6019 samples in 0.55s Traceback (most recent call last): File "/home/hwt/anaconda3/envs/streammapnet/lib/python3.8/site-packages/mmcv/utils/registry.py", line 69, in build_from_cfg return obj_cls(args) File "/home/hwt/network/StreamMapNet/plugin/datasets/nusc_dataset.py", line 28, in init super().init(kwargs) File "/home/hwt/network/StreamMapNet/plugin/datasets/base_dataset.py", line 73, in init self._set_sequence_group_flag() File "/home/hwt/network/StreamMapNet/plugin/datasets/base_dataset.py", line 87, in _set_sequence_group_flag if self.samples[idx]['prev'] == -1: KeyError: 'prev'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "tools/test.py", line 259, in main() File "tools/test.py", line 255, in main print(dataset.evaluate(outputs, **eval_kwargs)) File "/home/hwt/network/StreamMapNet/plugin/datasets/base_dataset.py", line 233, in evaluate return self._evaluate(result_path, logger=logger) File "/home/hwt/network/StreamMapNet/plugin/datasets/base_dataset.py", line 236, in _evaluate self.evaluator = VectorEvaluate(self.eval_config) File "/home/hwt/network/StreamMapNet/plugin/datasets/evaluation/vector_eval.py", line 33, in init self.dataset = build_dataset(dataset_cfg) File "/home/hwt/network/StreamMapNet/mmdetection3d/mmdet3d/datasets/builder.py", line 46, in build_dataset dataset = build_from_cfg(cfg, MMDET_DATASETS, default_args) File "/home/hwt/anaconda3/envs/streammapnet/lib/python3.8/site-packages/mmcv/utils/registry.py", line 72, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') KeyError: "NuscDataset: 'prev'"

[yuantianyuan01]

Hi, did you use our data converter to generate the annotation files?

[SherLockLi99]

Hi, did you use our data converter to generate the annotation files?

I've generated a new annotation file, but I'm testing the model under the old split