search

open-mmlab / OpenPCDet

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Apache License 2.0
4.62k stars 1.29k forks source link

error when training the model : AttributeError: __enter__ #201

Closed Jsijon closed 4 years ago

Jsijon commented 4 years ago

when i try to train the model (OpenPCDet v0.3.0 ) i get this error: merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch File "/home/john/OpenPCDet/tools/train_utils/train_utils.py", line 69, in train_model with tqdm.trange(start_epoch, total_epochs, desc='epochs', dynamic_ncols=True, leave=(rank == 0)) as tbar: AttributeError: enter

what is the problem?

sshaoshuai commented 4 years ago

Could you post the detail error log? I could help much with these few lines.

Jsijon commented 4 years ago

2020-08-01 20:02:46,663 INFO **Start logging** 2020-08-01 20:02:46,663 INFO CUDA_VISIBLE_DEVICES=ALL 2020-08-01 20:02:46,663 INFO cfg_file cfgs/kitti_models/pointpillar.yaml 2020-08-01 20:02:46,663 INFO batch_size 4 2020-08-01 20:02:46,663 INFO epochs 1 2020-08-01 20:02:46,663 INFO workers 8 2020-08-01 20:02:46,663 INFO extra_tag default 2020-08-01 20:02:46,663 INFO ckpt None 2020-08-01 20:02:46,663 INFO pretrained_model None 2020-08-01 20:02:46,664 INFO launcher none 2020-08-01 20:02:46,664 INFO tcp_port 18888 2020-08-01 20:02:46,664 INFO sync_bn False 2020-08-01 20:02:46,664 INFO fix_random_seed False 2020-08-01 20:02:46,664 INFO ckpt_save_interval 1 2020-08-01 20:02:46,664 INFO local_rank 0 2020-08-01 20:02:46,664 INFO max_ckpt_save_num 30 2020-08-01 20:02:46,664 INFO merge_all_iters_to_one_epoch False 2020-08-01 20:02:46,664 INFO set_cfgs None 2020-08-01 20:02:46,664 INFO max_waiting_mins 0 2020-08-01 20:02:46,664 INFO start_epoch 0 2020-08-01 20:02:46,664 INFO save_to_file False 2020-08-01 20:02:46,664 INFO cfg.ROOT_DIR: /home/john/OpenPCDet 2020-08-01 20:02:46,664 INFO cfg.LOCAL_RANK: 0 2020-08-01 20:02:46,664 INFO cfg.CLASS_NAMES: ['Car', 'Pedestrian', 'Cyclist'] 2020-08-01 20:02:46,664 INFO
cfg.DATA_CONFIG = edict() 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.DATASET: KittiDataset 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.DATA_PATH: ../data/kitti 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.POINT_CLOUD_RANGE: [0, -39.68, -3, 69.12, 39.68, 1] 2020-08-01 20:02:46,664 INFO
cfg.DATA_CONFIG.DATA_SPLIT = edict() 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.DATA_SPLIT.train: train 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.DATA_SPLIT.test: val 2020-08-01 20:02:46,664 INFO
cfg.DATA_CONFIG.INFO_PATH = edict() 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.INFO_PATH.train: ['kitti_infos_train.pkl'] 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.INFO_PATH.test: ['kitti_infos_val.pkl'] 2020-08-01 20:02:46,664 INFO cfg.DATA_CONFIG.FOV_POINTS_ONLY: True 2020-08-01 20:02:46,664 INFO
cfg.DATA_CONFIG.DATA_AUGMENTOR = edict() 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG.DATA_AUGMENTOR.DISABLE_AUG_LIST: ['placeholder'] 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG.DATA_AUGMENTOR.AUG_CONFIG_LIST: [{'NAME': 'gt_sampling', 'USE_ROAD_PLANE': True, 'DB_INFO_PATH': ['kitti_dbinfos_train.pkl'], 'PREPARE': {'filter_by_min_points': ['Car:5', 'Pedestrian:5', 'Cyclist:5'], 'filter_by_difficulty': [-1]}, 'SAMPLE_GROUPS': ['Car:15', 'Pedestrian:15', 'Cyclist:15'], 'NUM_POINT_FEATURES': 4, 'DATABASE_WITH_FAKELIDAR': False, 'REMOVE_EXTRA_WIDTH': [0.0, 0.0, 0.0], 'LIMIT_WHOLE_SCENE': False}, {'NAME': 'random_world_flip', 'ALONG_AXIS_LIST': ['x']}, {'NAME': 'random_world_rotation', 'WORLD_ROT_ANGLE': [-0.78539816, 0.78539816]}, {'NAME': 'random_world_scaling', 'WORLD_SCALE_RANGE': [0.95, 1.05]}] 2020-08-01 20:02:46,665 INFO
cfg.DATA_CONFIG.POINT_FEATURE_ENCODING = edict() 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.encoding_type: absolute_coordinates_encoding 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.used_feature_list: ['x', 'y', 'z', 'intensity'] 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.src_feature_list: ['x', 'y', 'z', 'intensity'] 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG.DATA_PROCESSOR: [{'NAME': 'mask_points_and_boxes_outside_range', 'REMOVE_OUTSIDE_BOXES': True}, {'NAME': 'shuffle_points', 'SHUFFLE_ENABLED': {'train': True, 'test': False}}, {'NAME': 'transform_points_to_voxels', 'VOXEL_SIZE': [0.16, 0.16, 4], 'MAX_POINTS_PER_VOXEL': 32, 'MAX_NUMBER_OF_VOXELS': {'train': 16000, 'test': 40000}}] 2020-08-01 20:02:46,665 INFO cfg.DATA_CONFIG._BASECONFIG: cfgs/dataset_configs/kitti_dataset.yaml 2020-08-01 20:02:46,665 INFO
cfg.MODEL = edict() 2020-08-01 20:02:46,665 INFO cfg.MODEL.NAME: PointPillar 2020-08-01 20:02:46,665 INFO
cfg.MODEL.VFE = edict() 2020-08-01 20:02:46,665 INFO cfg.MODEL.VFE.NAME: PillarVFE 2020-08-01 20:02:46,665 INFO cfg.MODEL.VFE.WITH_DISTANCE: False 2020-08-01 20:02:46,665 INFO cfg.MODEL.VFE.USE_ABSLOTE_XYZ: True 2020-08-01 20:02:46,665 INFO cfg.MODEL.VFE.USE_NORM: True 2020-08-01 20:02:46,665 INFO cfg.MODEL.VFE.NUM_FILTERS: [64] 2020-08-01 20:02:46,665 INFO
cfg.MODEL.MAP_TO_BEV = edict() 2020-08-01 20:02:46,665 INFO cfg.MODEL.MAP_TO_BEV.NAME: PointPillarScatter 2020-08-01 20:02:46,665 INFO cfg.MODEL.MAP_TO_BEV.NUM_BEV_FEATURES: 64 2020-08-01 20:02:46,665 INFO
cfg.MODEL.BACKBONE_2D = edict() 2020-08-01 20:02:46,665 INFO cfg.MODEL.BACKBONE_2D.NAME: BaseBEVBackbone 2020-08-01 20:02:46,665 INFO cfg.MODEL.BACKBONE_2D.LAYER_NUMS: [3, 5, 5] 2020-08-01 20:02:46,665 INFO cfg.MODEL.BACKBONE_2D.LAYER_STRIDES: [2, 2, 2] 2020-08-01 20:02:46,665 INFO cfg.MODEL.BACKBONE_2D.NUM_FILTERS: [64, 128, 256] 2020-08-01 20:02:46,665 INFO cfg.MODEL.BACKBONE_2D.UPSAMPLE_STRIDES: [1, 2, 4] 2020-08-01 20:02:46,666 INFO cfg.MODEL.BACKBONE_2D.NUM_UPSAMPLE_FILTERS: [128, 128, 128] 2020-08-01 20:02:46,666 INFO
cfg.MODEL.DENSE_HEAD = edict() 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.NAME: AnchorHeadSingle 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.CLASS_AGNOSTIC: False 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.USE_DIRECTION_CLASSIFIER: True 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.DIR_OFFSET: 0.78539 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.DIR_LIMIT_OFFSET: 0.0 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.NUM_DIR_BINS: 2 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.ANCHOR_GENERATOR_CONFIG: [{'class_name': 'Car', 'anchor_sizes': [[3.9, 1.6, 1.56]], 'anchor_rotations': [0, 1.57], 'anchor_bottom_heights': [-1.78], 'align_center': False, 'feature_map_stride': 2, 'matched_threshold': 0.6, 'unmatched_threshold': 0.45}, {'class_name': 'Pedestrian', 'anchor_sizes': [[0.8, 0.6, 1.73]], 'anchor_rotations': [0, 1.57], 'anchor_bottom_heights': [-0.6], 'align_center': False, 'feature_map_stride': 2, 'matched_threshold': 0.5, 'unmatched_threshold': 0.35}, {'class_name': 'Cyclist', 'anchor_sizes': [[1.76, 0.6, 1.73]], 'anchor_rotations': [0, 1.57], 'anchor_bottom_heights': [-0.6], 'align_center': False, 'feature_map_stride': 2, 'matched_threshold': 0.5, 'unmatched_threshold': 0.35}] 2020-08-01 20:02:46,666 INFO
cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG = edict() 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.NAME: AxisAlignedTargetAssigner 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.POS_FRACTION: -1.0 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.SAMPLE_SIZE: 512 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.NORM_BY_NUM_EXAMPLES: False 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.MATCH_HEIGHT: False 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.BOX_CODER: ResidualCoder 2020-08-01 20:02:46,666 INFO
cfg.MODEL.DENSE_HEAD.LOSS_CONFIG = edict() 2020-08-01 20:02:46,666 INFO
cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.cls_weight: 1.0 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.loc_weight: 2.0 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.dir_weight: 0.2 2020-08-01 20:02:46,666 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.code_weights: [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0] 2020-08-01 20:02:46,666 INFO
cfg.MODEL.POST_PROCESSING = edict() 2020-08-01 20:02:46,666 INFO cfg.MODEL.POST_PROCESSING.RECALL_THRESH_LIST: [0.3, 0.5, 0.7] 2020-08-01 20:02:46,666 INFO cfg.MODEL.POST_PROCESSING.SCORE_THRESH: 0.1 2020-08-01 20:02:46,666 INFO cfg.MODEL.POST_PROCESSING.OUTPUT_RAW_SCORE: False 2020-08-01 20:02:46,667 INFO cfg.MODEL.POST_PROCESSING.EVAL_METRIC: kitti 2020-08-01 20:02:46,667 INFO
cfg.MODEL.POST_PROCESSING.NMS_CONFIG = edict() 2020-08-01 20:02:46,667 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.MULTI_CLASSES_NMS: False 2020-08-01 20:02:46,667 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_TYPE: nms_gpu 2020-08-01 20:02:46,667 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_THRESH: 0.01 2020-08-01 20:02:46,667 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_PRE_MAXSIZE: 4096 2020-08-01 20:02:46,667 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_POST_MAXSIZE: 500 2020-08-01 20:02:46,667 INFO
cfg.OPTIMIZATION = edict() 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.BATCH_SIZE_PER_GPU: 4 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.NUM_EPOCHS: 80 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.OPTIMIZER: adam_onecycle 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.LR: 0.003 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.WEIGHT_DECAY: 0.01 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.MOMENTUM: 0.9 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.MOMS: [0.95, 0.85] 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.PCT_START: 0.4 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.DIV_FACTOR: 10 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.DECAY_STEP_LIST: [35, 45] 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.LR_DECAY: 0.1 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.LR_CLIP: 1e-07 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.LR_WARMUP: False 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.WARMUP_EPOCH: 1 2020-08-01 20:02:46,667 INFO cfg.OPTIMIZATION.GRAD_NORM_CLIP: 10 2020-08-01 20:02:46,667 INFO cfg.TAG: pointpillar 2020-08-01 20:02:46,667 INFO cfg.EXP_GROUP_PATH: kitti_models 2020-08-01 20:02:46,802 INFO Database filter by min points Car: 14357 => 13532 2020-08-01 20:02:46,802 INFO Database filter by min points Pedestrian: 2207 => 2168 2020-08-01 20:02:46,802 INFO Database filter by min points Cyclist: 734 => 705 2020-08-01 20:02:46,830 INFO Database filter by difficulty Car: 13532 => 10759 2020-08-01 20:02:46,834 INFO Database filter by difficulty Pedestrian: 2168 => 2075 2020-08-01 20:02:46,835 INFO Database filter by difficulty Cyclist: 705 => 581 2020-08-01 20:02:46,841 INFO Loading KITTI dataset 2020-08-01 20:02:46,948 INFO Total samples for KITTI dataset: 3712 2020-08-01 20:02:48,638 INFO PointPillar( (vfe): PillarVFE( (pfn_layers): ModuleList( (0): PFNLayer( (linear): Linear(in_features=10, out_features=64, bias=False) (norm): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (backbone_3d): None (map_to_bev_module): PointPillarScatter() (pfe): None (backbone_2d): BaseBEVBackbone( (blocks): ModuleList( (0): Sequential( (0): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), bias=False) (2): BatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (3): ReLU() (4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (5): BatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (6): ReLU() (7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (9): ReLU() (10): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (11): BatchNorm2d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (12): ReLU() ) (1): Sequential( (0): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0) (1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), bias=False) (2): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (3): ReLU() (4): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (5): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (6): ReLU() (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (9): ReLU() (10): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (11): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (12): ReLU() (13): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (14): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (15): ReLU() (16): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (17): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (18): ReLU() ) (2): Sequential( (0): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0) (1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), bias=False) (2): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (3): ReLU() (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (5): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (6): ReLU() (7): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (9): ReLU() (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (11): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (12): ReLU() (13): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (14): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (15): ReLU() (16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (17): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (18): ReLU() ) ) (deblocks): ModuleList( (0): Sequential( (0): ConvTranspose2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): ConvTranspose2d(128, 128, kernel_size=(2, 2), stride=(2, 2), bias=False) (1): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (2): Sequential( (0): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(4, 4), bias=False) (1): BatchNorm2d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) ) ) (dense_head): AnchorHeadSingle( (cls_loss_func): SigmoidFocalClassificationLoss() (reg_loss_func): WeightedSmoothL1Loss() (dir_loss_func): WeightedCrossEntropyLoss() (conv_cls): Conv2d(384, 18, kernel_size=(1, 1), stride=(1, 1)) (conv_box): Conv2d(384, 42, kernel_size=(1, 1), stride=(1, 1)) (conv_dir_cls): Conv2d(384, 12, kernel_size=(1, 1), stride=(1, 1)) ) (point_head): None (roi_head): None ) 2020-08-01 20:02:48,639 INFO **Start training kitti_models/pointpillar(default)** epochs: 0%| | 0/1 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 198, in main() File "train.py", line 170, in main merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch File "/home/john/OpenPCDet/tools/train_utils/train_utils.py", line 69, in train_model with tqdm.trange(start_epoch, total_epochs, desc='epochs', dynamic_ncols=True, leave=(rank == 0)) as tbar: AttributeError: enter

sshaoshuai commented 4 years ago

I never see this error before. Maybe it is related to the with statement of tqdm. You could try to re-install tqdm or refer to google for better understanding of this problem, just like https://stackoverflow.com/questions/51427729/python-error-attributeerror-enter.

Jsijon commented 4 years ago

i reinstalled tqdm and it works . thanks