search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.74k stars 9.48k forks source link

TypeError: class `RepeatDataset` in mmengine/dataset/dataset_wrapper.py: class `KittiDataset` in mmdet3d/datasets/kitti_dataset.py: The annotations loaded from annotation file should be a dict, but got <class 'list'>! #10262

Closed faziii0 closed 1 year ago

faziii0 commented 1 year ago

when i try to train it on kitti dataset got this error

python tools/train.py configs/pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py 05/04 16:32:52 - mmengine - INFO -

System environment: sys.platform: linux Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1275144488 GPU 0: NVIDIA GeForce RTX 3080 Ti CUDA_HOME: /home/fazal/anaconda3/envs/mmd NVCC: Cuda compilation tools, release 11.6, V11.6.124 GCC: gcc (Ubuntu 11.3.0-1ubuntu1~22.04) 11.3.0 PyTorch: 1.13.1 PyTorch compiling details: PyTorch built with:

Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: none Distributed training: False GPU number: 1

05/04 16:32:53 - mmengine - INFO - Config: voxel_size = [0.16, 0.16, 4] model = dict( type='VoxelNet', data_preprocessor=dict( type='Det3DDataPreprocessor', voxel=True, voxel_layer=dict( max_num_points=32, point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1], voxel_size=[0.16, 0.16, 4], max_voxels=(16000, 40000))), voxel_encoder=dict( type='PillarFeatureNet', in_channels=4, feat_channels=[64], with_distance=False, voxel_size=[0.16, 0.16, 4], point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]), middle_encoder=dict( type='PointPillarsScatter', in_channels=64, output_shape=[496, 432]), backbone=dict( type='SECOND', in_channels=64, layer_nums=[3, 5, 5], layer_strides=[2, 2, 2], out_channels=[64, 128, 256]), neck=dict( type='SECONDFPN', in_channels=[64, 128, 256], upsample_strides=[1, 2, 4], out_channels=[128, 128, 128]), bbox_head=dict( type='Anchor3DHead', num_classes=3, in_channels=384, feat_channels=384, use_direction_classifier=True, assign_per_class=True, anchor_generator=dict( type='AlignedAnchor3DRangeGenerator', ranges=[[0, -39.68, -0.6, 69.12, 39.68, -0.6], [0, -39.68, -0.6, 69.12, 39.68, -0.6], [0, -39.68, -1.78, 69.12, 39.68, -1.78]], sizes=[[0.8, 0.6, 1.73], [1.76, 0.6, 1.73], [3.9, 1.6, 1.56]], rotations=[0, 1.57], reshape_out=False), diff_rad_by_sin=True, bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'), loss_cls=dict( type='mmdet.FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict( type='mmdet.SmoothL1Loss', beta=0.1111111111111111, loss_weight=2.0), loss_dir=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=0.2)), train_cfg=dict( assigner=[ dict( type='Max3DIoUAssigner', iou_calculator=dict(type='mmdet3d.BboxOverlapsNearest3D'), pos_iou_thr=0.5, neg_iou_thr=0.35, min_pos_iou=0.35, ignore_iof_thr=-1), dict( type='Max3DIoUAssigner', iou_calculator=dict(type='mmdet3d.BboxOverlapsNearest3D'), pos_iou_thr=0.5, neg_iou_thr=0.35, min_pos_iou=0.35, ignore_iof_thr=-1), dict( type='Max3DIoUAssigner', iou_calculator=dict(type='mmdet3d.BboxOverlapsNearest3D'), pos_iou_thr=0.6, neg_iou_thr=0.45, min_pos_iou=0.45, ignore_iof_thr=-1) ], allowed_border=0, pos_weight=-1, debug=False), test_cfg=dict( use_rotate_nms=True, nms_across_levels=False, nms_thr=0.01, score_thr=0.1, min_bbox_size=0, nms_pre=100, max_num=50)) dataset_type = 'KittiDataset' data_root = 'data/kitti/' class_names = ['Pedestrian', 'Cyclist', 'Car'] point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1] input_modality = dict(use_lidar=True, use_camera=False) metainfo = dict(classes=['Pedestrian', 'Cyclist', 'Car']) backend_args = None db_sampler = dict( data_root='data/kitti/', info_path='data/kitti/kitti_dbinfos_train.pkl', rate=1.0, prepare=dict( filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5, Pedestrian=5, Cyclist=5)), classes=['Pedestrian', 'Cyclist', 'Car'], sample_groups=dict(Car=15, Pedestrian=15, Cyclist=15), points_loader=dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), backend_args=None) train_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True), dict( type='ObjectSample', db_sampler=dict( data_root='data/kitti/', info_path='data/kitti/kitti_dbinfos_train.pkl', rate=1.0, prepare=dict( filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5, Pedestrian=5, Cyclist=5)), classes=['Pedestrian', 'Cyclist', 'Car'], sample_groups=dict(Car=15, Pedestrian=15, Cyclist=15), points_loader=dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), backend_args=None), use_ground_plane=True), dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5), dict( type='GlobalRotScaleTrans', rot_range=[-0.78539816, 0.78539816], scale_ratio_range=[0.95, 1.05]), dict( type='PointsRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]), dict( type='ObjectRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]), dict(type='PointShuffle'), dict( type='Pack3DDetInputs', keys=['points', 'gt_labels_3d', 'gt_bboxes_3d']) ] test_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), dict( type='MultiScaleFlipAug3D', img_scale=(1333, 800), pts_scale_ratio=1, flip=False, transforms=[ dict( type='GlobalRotScaleTrans', rot_range=[0, 0], scale_ratio_range=[1.0, 1.0], translation_std=[0, 0, 0]), dict(type='RandomFlip3D'), dict( type='PointsRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]) ]), dict(type='Pack3DDetInputs', keys=['points']) ] eval_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), dict(type='Pack3DDetInputs', keys=['points']) ] train_dataloader = dict( batch_size=6, num_workers=4, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=2, dataset=dict( type='KittiDataset', data_root='data/kitti/', ann_file='kitti_infos_train.pkl', data_prefix=dict(pts='training/velodyne_reduced'), pipeline=[ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), dict( type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True), dict( type='ObjectSample', db_sampler=dict( data_root='data/kitti/', info_path='data/kitti/kitti_dbinfos_train.pkl', rate=1.0, prepare=dict( filter_by_difficulty=[-1], filter_by_min_points=dict( Car=5, Pedestrian=5, Cyclist=5)), classes=['Pedestrian', 'Cyclist', 'Car'], sample_groups=dict(Car=15, Pedestrian=15, Cyclist=15), points_loader=dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), backend_args=None), use_ground_plane=True), dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5), dict( type='GlobalRotScaleTrans', rot_range=[-0.78539816, 0.78539816], scale_ratio_range=[0.95, 1.05]), dict( type='PointsRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]), dict( type='ObjectRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]), dict(type='PointShuffle'), dict( type='Pack3DDetInputs', keys=['points', 'gt_labels_3d', 'gt_bboxes_3d']) ], modality=dict(use_lidar=True, use_camera=False), test_mode=False, metainfo=dict(classes=['Pedestrian', 'Cyclist', 'Car']), box_type_3d='LiDAR', backend_args=None))) val_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='KittiDataset', data_root='data/kitti/', data_prefix=dict(pts='training/velodyne_reduced'), ann_file='kitti_infos_val.pkl', pipeline=[ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), dict( type='MultiScaleFlipAug3D', img_scale=(1333, 800), pts_scale_ratio=1, flip=False, transforms=[ dict( type='GlobalRotScaleTrans', rot_range=[0, 0], scale_ratio_range=[1.0, 1.0], translation_std=[0, 0, 0]), dict(type='RandomFlip3D'), dict( type='PointsRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]) ]), dict(type='Pack3DDetInputs', keys=['points']) ], modality=dict(use_lidar=True, use_camera=False), test_mode=True, metainfo=dict(classes=['Pedestrian', 'Cyclist', 'Car']), box_type_3d='LiDAR', backend_args=None)) test_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='KittiDataset', data_root='data/kitti/', data_prefix=dict(pts='training/velodyne_reduced'), ann_file='kitti_infos_val.pkl', pipeline=[ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, backend_args=None), dict( type='MultiScaleFlipAug3D', img_scale=(1333, 800), pts_scale_ratio=1, flip=False, transforms=[ dict( type='GlobalRotScaleTrans', rot_range=[0, 0], scale_ratio_range=[1.0, 1.0], translation_std=[0, 0, 0]), dict(type='RandomFlip3D'), dict( type='PointsRangeFilter', point_cloud_range=[0, -39.68, -3, 69.12, 39.68, 1]) ]), dict(type='Pack3DDetInputs', keys=['points']) ], modality=dict(use_lidar=True, use_camera=False), test_mode=True, metainfo=dict(classes=['Pedestrian', 'Cyclist', 'Car']), box_type_3d='LiDAR', backend_args=None)) val_evaluator = dict( type='KittiMetric', ann_file='data/kitti/kitti_infos_val.pkl', metric='bbox', backend_args=None) test_evaluator = dict( type='KittiMetric', ann_file='data/kitti/kitti_infos_val.pkl', metric='bbox', backend_args=None) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='Det3DLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') lr = 0.001 optim_wrapper = dict( type='OptimWrapper', optimizer=dict( type='AdamW', lr=0.001, betas=(0.95, 0.99), weight_decay=0.01), clip_grad=dict(max_norm=35, norm_type=2)) param_scheduler = [ dict( type='CosineAnnealingLR', T_max=32.0, eta_min=0.01, begin=0, end=32.0, by_epoch=True, convert_to_iter_based=True), dict( type='CosineAnnealingLR', T_max=48.0, eta_min=1.0000000000000001e-07, begin=32.0, end=80, by_epoch=True, convert_to_iter_based=True), dict( type='CosineAnnealingMomentum', T_max=32.0, eta_min=0.8947368421052632, begin=0, end=32.0, by_epoch=True, convert_to_iter_based=True), dict( type='CosineAnnealingMomentum', T_max=48.0, eta_min=1, begin=32.0, end=80, convert_to_iter_based=True) ] train_cfg = dict(by_epoch=True, max_epochs=80, val_interval=2) val_cfg = dict() test_cfg = dict() auto_scale_lr = dict(enable=False, base_batch_size=48) default_scope = 'mmdet3d' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=-1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='Det3DVisualizationHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = False epoch_num = 80 launcher = 'none' work_dir = './work_dirs/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class'

/home/fazal/Downloads/UQ/mmd3d/mmdetection3d/mmdet3d/models/dense_heads/anchor3d_head.py:92: UserWarning: dir_offset and dir_limit_offset will be depressed and be incorporated into box coder in the future warnings.warn( 05/04 16:32:55 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used. 05/04 16:32:55 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook
(BELOW_NORMAL) LoggerHook

before_train: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(VERY_LOW ) CheckpointHook

before_train_epoch: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(NORMAL ) DistSamplerSeedHook

before_train_iter: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook

after_train_iter: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook

after_train_epoch: (NORMAL ) IterTimerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook

before_val_epoch: (NORMAL ) IterTimerHook

before_val_iter: (NORMAL ) IterTimerHook

after_val_iter: (NORMAL ) IterTimerHook
(NORMAL ) Det3DVisualizationHook
(BELOW_NORMAL) LoggerHook

after_val_epoch: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook

after_train: (VERY_LOW ) CheckpointHook

before_test_epoch: (NORMAL ) IterTimerHook

before_test_iter: (NORMAL ) IterTimerHook

after_test_iter: (NORMAL ) IterTimerHook
(NORMAL ) Det3DVisualizationHook
(BELOW_NORMAL) LoggerHook

after_test_epoch: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook

after_run: (BELOW_NORMAL) LoggerHook

05/04 16:32:55 - mmengine - INFO - load 14357 Car database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 2207 Pedestrian database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 734 Cyclist database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 1297 Van database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 56 Person_sitting database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 488 Truck database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 224 Tram database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 337 Misc database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - After filter database: 05/04 16:32:55 - mmengine - INFO - load 10520 Car database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 2066 Pedestrian database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 580 Cyclist database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 826 Van database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 53 Person_sitting database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 321 Truck database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 199 Tram database infos in DataBaseSampler 05/04 16:32:55 - mmengine - INFO - load 259 Misc database infos in DataBaseSampler Traceback (most recent call last): File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 122, in build_from_cfg obj = obj_cls(**args) # type: ignore File "/home/fazal/Downloads/UQ/mmd3d/mmdetection3d/mmdet3d/datasets/kitti_dataset.py", line 77, in init super().init( File "/home/fazal/Downloads/UQ/mmd3d/mmdetection3d/mmdet3d/datasets/det3d_dataset.py", line 129, in init super().init( File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/dataset/base_dataset.py", line 250, in init self.full_init() File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/dataset/base_dataset.py", line 301, in full_init self.data_list = self.load_data_list() File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/dataset/base_dataset.py", line 440, in load_data_list raise TypeError(f'The annotations loaded from annotation file ' TypeError: The annotations loaded from annotation file should be a dict, but got <class 'list'>!

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 122, in build_from_cfg obj = obj_cls(*args) # type: ignore File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/dataset/dataset_wrapper.py", line 211, in init self.dataset = DATASETS.build(dataset) File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/registry/registry.py", line 548, in build return self.build_func(cfg, args, **kwargs, registry=self) File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 144, in build_from_cfg raise type(e)( TypeError: class KittiDataset in mmdet3d/datasets/kitti_dataset.py: The annotations loaded from annotation file should be a dict, but got <class 'list'>!

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "tools/train.py", line 135, in main() File "tools/train.py", line 131, in main runner.train() File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1687, in train self._train_loop = self.build_train_loop( File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1486, in build_train_loop loop = EpochBasedTrainLoop( File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/runner/loops.py", line 44, in init super().init(runner, dataloader) File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/runner/base_loop.py", line 26, in init self.dataloader = runner.build_dataloader( File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1346, in build_dataloader dataset = DATASETS.build(dataset_cfg) File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/registry/registry.py", line 548, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "/home/fazal/anaconda3/envs/mmd/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 144, in build_from_cfg raise type(e)( TypeError: class RepeatDataset in mmengine/dataset/dataset_wrapper.py: class KittiDataset in mmdet3d/datasets/kitti_dataset.py: The annotations loaded from annotation file should be a dict, but got <class 'list'>!

hhaAndroid commented 1 year ago

@faziii0 Please go to mmdet3d to create the issue, thanks!