search

open-mmlab / OpenPCDet

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Apache License 2.0
4.68k stars 1.3k forks source link

How to solve train problem #820

Closed VsionQing closed 2 years ago

VsionQing commented 2 years ago

log_train_20220223-093029.txt Log file as above There is no error message, but the training is not successful

VsionQing commented 2 years ago

2022-02-23 09:30:29,155 INFO **Start logging** 2022-02-23 09:30:29,155 INFO CUDA_VISIBLE_DEVICES=ALL 2022-02-23 09:30:29,156 INFO cfg_file cfgs/kitti_models/pv_rcnn.yaml 2022-02-23 09:30:29,156 INFO batch_size 1 2022-02-23 09:30:29,156 INFO epochs 80 2022-02-23 09:30:29,156 INFO workers 1 2022-02-23 09:30:29,156 INFO extra_tag default 2022-02-23 09:30:29,156 INFO ckpt None 2022-02-23 09:30:29,156 INFO pretrained_model None 2022-02-23 09:30:29,156 INFO launcher none 2022-02-23 09:30:29,157 INFO tcp_port 18888 2022-02-23 09:30:29,157 INFO sync_bn False 2022-02-23 09:30:29,157 INFO fix_random_seed False 2022-02-23 09:30:29,157 INFO ckpt_save_interval 1 2022-02-23 09:30:29,157 INFO local_rank 0 2022-02-23 09:30:29,157 INFO max_ckpt_save_num 30 2022-02-23 09:30:29,157 INFO merge_all_iters_to_one_epoch False 2022-02-23 09:30:29,157 INFO set_cfgs None 2022-02-23 09:30:29,157 INFO max_waiting_mins 0 2022-02-23 09:30:29,157 INFO start_epoch 0 2022-02-23 09:30:29,158 INFO num_epochs_to_eval 0 2022-02-23 09:30:29,158 INFO save_to_file False 2022-02-23 09:30:29,158 INFO cfg.ROOT_DIR: E:\PythonFile\OpenPCDet-master1 2022-02-23 09:30:29,158 INFO cfg.LOCAL_RANK: 0 2022-02-23 09:30:29,158 INFO cfg.CLASS_NAMES: ['Car', 'Pedestrian', 'Cyclist'] 2022-02-23 09:30:29,158 INFO
cfg.DATA_CONFIG = edict() 2022-02-23 09:30:29,158 INFO cfg.DATA_CONFIG.DATASET: KittiDataset 2022-02-23 09:30:29,158 INFO cfg.DATA_CONFIG.DATA_PATH: ../data/kitti 2022-02-23 09:30:29,158 INFO cfg.DATA_CONFIG.POINT_CLOUD_RANGE: [0, -40, -3, 70.4, 40, 1] 2022-02-23 09:30:29,158 INFO
cfg.DATA_CONFIG.DATA_SPLIT = edict() 2022-02-23 09:30:29,158 INFO cfg.DATA_CONFIG.DATA_SPLIT.train: train 2022-02-23 09:30:29,158 INFO cfg.DATA_CONFIG.DATA_SPLIT.test: val 2022-02-23 09:30:29,159 INFO
cfg.DATA_CONFIG.INFO_PATH = edict() 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.INFO_PATH.train: ['kitti_infos_train.pkl'] 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.INFO_PATH.test: ['kitti_infos_val.pkl'] 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.GET_ITEM_LIST: ['points'] 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.FOV_POINTS_ONLY: True 2022-02-23 09:30:29,159 INFO
cfg.DATA_CONFIG.DATA_AUGMENTOR = edict() 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.DATA_AUGMENTOR.DISABLE_AUG_LIST: ['placeholder'] 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.DATA_AUGMENTOR.AUG_CONFIG_LIST: [{'NAME': 'gt_sampling', 'USE_ROAD_PLANE': False, '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:10', 'Cyclist:10'], '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]}] 2022-02-23 09:30:29,159 INFO
cfg.DATA_CONFIG.POINT_FEATURE_ENCODING = edict() 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.encoding_type: absolute_coordinates_encoding 2022-02-23 09:30:29,159 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.used_feature_list: ['x', 'y', 'z', 'intensity'] 2022-02-23 09:30:29,160 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.src_feature_list: ['x', 'y', 'z', 'intensity'] 2022-02-23 09:30:29,160 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': [0.05, 0.05, 0.1], 'MAX_POINTS_PER_VOXEL': 5, 'MAX_NUMBER_OF_VOXELS': {'train': 16000, 'test': 40000}}] 2022-02-23 09:30:29,160 INFO cfg.DATA_CONFIG._BASECONFIG: cfgs/dataset_configs/kitti_dataset.yaml 2022-02-23 09:30:29,160 INFO
cfg.MODEL = edict() 2022-02-23 09:30:29,160 INFO cfg.MODEL.NAME: PVRCNN 2022-02-23 09:30:29,160 INFO
cfg.MODEL.VFE = edict() 2022-02-23 09:30:29,160 INFO cfg.MODEL.VFE.NAME: MeanVFE 2022-02-23 09:30:29,160 INFO
cfg.MODEL.BACKBONE_3D = edict() 2022-02-23 09:30:29,160 INFO cfg.MODEL.BACKBONE_3D.NAME: VoxelBackBone8x 2022-02-23 09:30:29,161 INFO
cfg.MODEL.MAP_TO_BEV = edict() 2022-02-23 09:30:29,161 INFO cfg.MODEL.MAP_TO_BEV.NAME: HeightCompression 2022-02-23 09:30:29,161 INFO cfg.MODEL.MAP_TO_BEV.NUM_BEV_FEATURES: 256 2022-02-23 09:30:29,161 INFO
cfg.MODEL.BACKBONE_2D = edict() 2022-02-23 09:30:29,161 INFO cfg.MODEL.BACKBONE_2D.NAME: BaseBEVBackbone 2022-02-23 09:30:29,161 INFO cfg.MODEL.BACKBONE_2D.LAYER_NUMS: [5, 5] 2022-02-23 09:30:29,161 INFO cfg.MODEL.BACKBONE_2D.LAYER_STRIDES: [1, 2] 2022-02-23 09:30:29,161 INFO cfg.MODEL.BACKBONE_2D.NUM_FILTERS: [128, 256] 2022-02-23 09:30:29,161 INFO cfg.MODEL.BACKBONE_2D.UPSAMPLE_STRIDES: [1, 2] 2022-02-23 09:30:29,161 INFO cfg.MODEL.BACKBONE_2D.NUM_UPSAMPLE_FILTERS: [256, 256] 2022-02-23 09:30:29,161 INFO
cfg.MODEL.DENSE_HEAD = edict() 2022-02-23 09:30:29,161 INFO cfg.MODEL.DENSE_HEAD.NAME: AnchorHeadSingle 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.CLASS_AGNOSTIC: False 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.USE_DIRECTION_CLASSIFIER: True 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.DIR_OFFSET: 0.78539 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.DIR_LIMIT_OFFSET: 0.0 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.NUM_DIR_BINS: 2 2022-02-23 09:30:29,162 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': 8, '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': 8, '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': 8, 'matched_threshold': 0.5, 'unmatched_threshold': 0.35}] 2022-02-23 09:30:29,162 INFO
cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG = edict() 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.NAME: AxisAlignedTargetAssigner 2022-02-23 09:30:29,162 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.POS_FRACTION: -1.0 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.SAMPLE_SIZE: 512 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.NORM_BY_NUM_EXAMPLES: False 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.MATCH_HEIGHT: False 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.BOX_CODER: ResidualCoder 2022-02-23 09:30:29,163 INFO
cfg.MODEL.DENSE_HEAD.LOSS_CONFIG = edict() 2022-02-23 09:30:29,163 INFO
cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.cls_weight: 1.0 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.loc_weight: 2.0 2022-02-23 09:30:29,163 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.dir_weight: 0.2 2022-02-23 09:30:29,163 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] 2022-02-23 09:30:29,163 INFO
cfg.MODEL.PFE = edict() 2022-02-23 09:30:29,163 INFO cfg.MODEL.PFE.NAME: VoxelSetAbstraction 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.POINT_SOURCE: raw_points 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.NUM_KEYPOINTS: 2048 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.NUM_OUTPUT_FEATURES: 128 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.SAMPLE_METHOD: FPS 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.FEATURES_SOURCE: ['bev', 'x_conv1', 'x_conv2', 'x_conv3', 'x_conv4', 'raw_points'] 2022-02-23 09:30:29,164 INFO
cfg.MODEL.PFE.SA_LAYER = edict() 2022-02-23 09:30:29,164 INFO
cfg.MODEL.PFE.SA_LAYER.raw_points = edict() 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.SA_LAYER.raw_points.MLPS: [[16, 16], [16, 16]] 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.SA_LAYER.raw_points.POOL_RADIUS: [0.4, 0.8] 2022-02-23 09:30:29,164 INFO cfg.MODEL.PFE.SA_LAYER.raw_points.NSAMPLE: [16, 16] 2022-02-23 09:30:29,164 INFO
cfg.MODEL.PFE.SA_LAYER.x_conv1 = edict() 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.DOWNSAMPLE_FACTOR: 1 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.MLPS: [[16, 16], [16, 16]] 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.POOL_RADIUS: [0.4, 0.8] 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.NSAMPLE: [16, 16] 2022-02-23 09:30:29,165 INFO
cfg.MODEL.PFE.SA_LAYER.x_conv2 = edict() 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.DOWNSAMPLE_FACTOR: 2 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.MLPS: [[32, 32], [32, 32]] 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.POOL_RADIUS: [0.8, 1.2] 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.NSAMPLE: [16, 32] 2022-02-23 09:30:29,165 INFO
cfg.MODEL.PFE.SA_LAYER.x_conv3 = edict() 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.DOWNSAMPLE_FACTOR: 4 2022-02-23 09:30:29,165 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.MLPS: [[64, 64], [64, 64]] 2022-02-23 09:30:29,166 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.POOL_RADIUS: [1.2, 2.4] 2022-02-23 09:30:29,166 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.NSAMPLE: [16, 32] 2022-02-23 09:30:29,166 INFO
cfg.MODEL.PFE.SA_LAYER.x_conv4 = edict() 2022-02-23 09:30:29,166 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.DOWNSAMPLE_FACTOR: 8 2022-02-23 09:30:29,166 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.MLPS: [[64, 64], [64, 64]] 2022-02-23 09:30:29,166 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.POOL_RADIUS: [2.4, 4.8] 2022-02-23 09:30:29,166 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.NSAMPLE: [16, 32] 2022-02-23 09:30:29,166 INFO
cfg.MODEL.POINT_HEAD = edict() 2022-02-23 09:30:29,166 INFO cfg.MODEL.POINT_HEAD.NAME: PointHeadSimple 2022-02-23 09:30:29,166 INFO cfg.MODEL.POINT_HEAD.CLS_FC: [256, 256] 2022-02-23 09:30:29,166 INFO cfg.MODEL.POINT_HEAD.CLASS_AGNOSTIC: True 2022-02-23 09:30:29,166 INFO cfg.MODEL.POINT_HEAD.USE_POINT_FEATURES_BEFORE_FUSION: True 2022-02-23 09:30:29,167 INFO
cfg.MODEL.POINT_HEAD.TARGET_CONFIG = edict() 2022-02-23 09:30:29,167 INFO cfg.MODEL.POINT_HEAD.TARGET_CONFIG.GT_EXTRA_WIDTH: [0.2, 0.2, 0.2] 2022-02-23 09:30:29,167 INFO
cfg.MODEL.POINT_HEAD.LOSS_CONFIG = edict() 2022-02-23 09:30:29,167 INFO cfg.MODEL.POINT_HEAD.LOSS_CONFIG.LOSS_REG: smooth-l1 2022-02-23 09:30:29,167 INFO
cfg.MODEL.POINT_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2022-02-23 09:30:29,167 INFO cfg.MODEL.POINT_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.point_cls_weight: 1.0 2022-02-23 09:30:29,167 INFO
cfg.MODEL.ROI_HEAD = edict() 2022-02-23 09:30:29,167 INFO cfg.MODEL.ROI_HEAD.NAME: PVRCNNHead 2022-02-23 09:30:29,167 INFO cfg.MODEL.ROI_HEAD.CLASS_AGNOSTIC: True 2022-02-23 09:30:29,167 INFO cfg.MODEL.ROI_HEAD.SHARED_FC: [256, 256] 2022-02-23 09:30:29,167 INFO cfg.MODEL.ROI_HEAD.CLS_FC: [256, 256] 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.REG_FC: [256, 256] 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.DP_RATIO: 0.3 2022-02-23 09:30:29,168 INFO
cfg.MODEL.ROI_HEAD.NMS_CONFIG = edict() 2022-02-23 09:30:29,168 INFO
cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN = edict() 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_TYPE: nms_gpu 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.MULTI_CLASSES_NMS: False 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_PRE_MAXSIZE: 9000 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_POST_MAXSIZE: 512 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_THRESH: 0.8 2022-02-23 09:30:29,168 INFO
cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST = edict() 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_TYPE: nms_gpu 2022-02-23 09:30:29,168 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.MULTI_CLASSES_NMS: False 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_PRE_MAXSIZE: 1024 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_POST_MAXSIZE: 100 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_THRESH: 0.7 2022-02-23 09:30:29,169 INFO
cfg.MODEL.ROI_HEAD.ROI_GRID_POOL = edict() 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.GRID_SIZE: 6 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.MLPS: [[64, 64], [64, 64]] 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.POOL_RADIUS: [0.8, 1.6] 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.NSAMPLE: [16, 16] 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.POOL_METHOD: max_pool 2022-02-23 09:30:29,169 INFO
cfg.MODEL.ROI_HEAD.TARGET_CONFIG = edict() 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.BOX_CODER: ResidualCoder 2022-02-23 09:30:29,169 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.ROI_PER_IMAGE: 128 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.FG_RATIO: 0.5 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.SAMPLE_ROI_BY_EACH_CLASS: True 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_SCORE_TYPE: roi_iou 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_FG_THRESH: 0.75 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_BG_THRESH: 0.25 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_BG_THRESH_LO: 0.1 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.HARD_BG_RATIO: 0.8 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.REG_FG_THRESH: 0.55 2022-02-23 09:30:29,170 INFO
cfg.MODEL.ROI_HEAD.LOSS_CONFIG = edict() 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.CLS_LOSS: BinaryCrossEntropy 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.REG_LOSS: smooth-l1 2022-02-23 09:30:29,170 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.CORNER_LOSS_REGULARIZATION: True 2022-02-23 09:30:29,171 INFO
cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2022-02-23 09:30:29,171 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.rcnn_cls_weight: 1.0 2022-02-23 09:30:29,171 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.rcnn_reg_weight: 1.0 2022-02-23 09:30:29,171 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.rcnn_corner_weight: 1.0 2022-02-23 09:30:29,171 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.code_weights: [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0] 2022-02-23 09:30:29,171 INFO
cfg.MODEL.POST_PROCESSING = edict() 2022-02-23 09:30:29,171 INFO cfg.MODEL.POST_PROCESSING.RECALL_THRESH_LIST: [0.3, 0.5, 0.7] 2022-02-23 09:30:29,171 INFO cfg.MODEL.POST_PROCESSING.SCORE_THRESH: 0.1 2022-02-23 09:30:29,171 INFO cfg.MODEL.POST_PROCESSING.OUTPUT_RAW_SCORE: False 2022-02-23 09:30:29,171 INFO cfg.MODEL.POST_PROCESSING.EVAL_METRIC: kitti 2022-02-23 09:30:29,171 INFO
cfg.MODEL.POST_PROCESSING.NMS_CONFIG = edict() 2022-02-23 09:30:29,171 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.MULTI_CLASSES_NMS: False 2022-02-23 09:30:29,172 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_TYPE: nms_gpu 2022-02-23 09:30:29,172 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_THRESH: 0.1 2022-02-23 09:30:29,172 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_PRE_MAXSIZE: 4096 2022-02-23 09:30:29,172 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_POST_MAXSIZE: 500 2022-02-23 09:30:29,172 INFO
cfg.OPTIMIZATION = edict() 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.BATCH_SIZE_PER_GPU: 2 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.NUM_EPOCHS: 80 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.OPTIMIZER: adam_onecycle 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.LR: 0.01 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.WEIGHT_DECAY: 0.01 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.MOMENTUM: 0.9 2022-02-23 09:30:29,172 INFO cfg.OPTIMIZATION.MOMS: [0.95, 0.85] 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.PCT_START: 0.4 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.DIV_FACTOR: 10 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.DECAY_STEP_LIST: [35, 45] 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.LR_DECAY: 0.1 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.LR_CLIP: 1e-07 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.LR_WARMUP: False 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.WARMUP_EPOCH: 1 2022-02-23 09:30:29,173 INFO cfg.OPTIMIZATION.GRAD_NORM_CLIP: 10 2022-02-23 09:30:29,173 INFO cfg.TAG: pv_rcnn 2022-02-23 09:30:29,173 INFO cfg.EXP_GROUP_PATH: kitti_models 2022-02-23 09:30:29,280 INFO Database filter by min points Car: 14357 => 13532 2022-02-23 09:30:29,281 INFO Database filter by min points Pedestrian: 2207 => 2168 2022-02-23 09:30:29,281 INFO Database filter by min points Cyclist: 734 => 705 2022-02-23 09:30:29,283 INFO Database filter by difficulty Car: 13532 => 10759 2022-02-23 09:30:29,284 INFO Database filter by difficulty Pedestrian: 2168 => 2075 2022-02-23 09:30:29,284 INFO Database filter by difficulty Cyclist: 705 => 581 2022-02-23 09:30:29,289 INFO Loading KITTI dataset 2022-02-23 09:30:29,369 INFO Total samples for KITTI dataset: 3712 2022-02-23 09:30:30,574 INFO PVRCNN( (vfe): MeanVFE() (backbone_3d): VoxelBackBone8x( (conv_input): SparseSequential( (0): SubMConv3d(4, 16, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[1, 1, 1], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (conv1): SparseSequential( (0): SparseSequential( (0): SubMConv3d(16, 16, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) ) (conv2): SparseSequential( (0): SparseSequential( (0): SparseConv3d(16, 32, kernel_size=[3, 3, 3], stride=[2, 2, 2], padding=[1, 1, 1], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (1): SparseSequential( (0): SubMConv3d(32, 32, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (2): SparseSequential( (0): SubMConv3d(32, 32, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(32, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) ) (conv3): SparseSequential( (0): SparseSequential( (0): SparseConv3d(32, 64, kernel_size=[3, 3, 3], stride=[2, 2, 2], padding=[1, 1, 1], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (1): SparseSequential( (0): SubMConv3d(64, 64, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (2): SparseSequential( (0): SubMConv3d(64, 64, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) ) (conv4): SparseSequential( (0): SparseSequential( (0): SparseConv3d(64, 64, kernel_size=[3, 3, 3], stride=[2, 2, 2], padding=[0, 1, 1], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (1): SparseSequential( (0): SubMConv3d(64, 64, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (2): SparseSequential( (0): SubMConv3d(64, 64, kernel_size=[3, 3, 3], stride=[1, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(64, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) ) (conv_out): SparseSequential( (0): SparseConv3d(64, 128, kernel_size=[3, 1, 1], stride=[2, 1, 1], padding=[0, 0, 0], dilation=[1, 1, 1], output_padding=[0, 0, 0], bias=False, algo=ConvAlgo.MaskImplicitGemm) (1): BatchNorm1d(128, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) ) (map_to_bev_module): HeightCompression() (pfe): VoxelSetAbstraction( (SA_layers): ModuleList( (0): StackSAModuleMSG( (groupers): ModuleList( (0): QueryAndGroup() (1): QueryAndGroup() ) (mlps): ModuleList( (0): Sequential( (0): Conv2d(19, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) (1): Sequential( (0): Conv2d(19, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) ) ) (1): StackSAModuleMSG( (groupers): ModuleList( (0): QueryAndGroup() (1): QueryAndGroup() ) (mlps): ModuleList( (0): Sequential( (0): Conv2d(35, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) (1): Sequential( (0): Conv2d(35, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) ) ) (2): StackSAModuleMSG( (groupers): ModuleList( (0): QueryAndGroup() (1): QueryAndGroup() ) (mlps): ModuleList( (0): Sequential( (0): Conv2d(67, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) (1): Sequential( (0): Conv2d(67, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) ) ) (3): StackSAModuleMSG( (groupers): ModuleList( (0): QueryAndGroup() (1): QueryAndGroup() ) (mlps): ModuleList( (0): Sequential( (0): Conv2d(67, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) (1): Sequential( (0): Conv2d(67, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) ) ) ) (SA_rawpoints): StackSAModuleMSG( (groupers): ModuleList( (0): QueryAndGroup() (1): QueryAndGroup() ) (mlps): ModuleList( (0): Sequential( (0): Conv2d(4, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) (1): Sequential( (0): Conv2d(4, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) ) ) (vsa_point_feature_fusion): Sequential( (0): Linear(in_features=640, out_features=128, bias=False) (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) ) (backbone_2d): BaseBEVBackbone( (blocks): ModuleList( (0): Sequential( (0): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0) (1): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), 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() ) (1): 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(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(256, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU() ) (1): Sequential( (0): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2), bias=False) (1): BatchNorm2d(256, 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(512, 18, kernel_size=(1, 1), stride=(1, 1)) (conv_box): Conv2d(512, 42, kernel_size=(1, 1), stride=(1, 1)) (conv_dir_cls): Conv2d(512, 12, kernel_size=(1, 1), stride=(1, 1)) ) (point_head): PointHeadSimple( (cls_loss_func): SigmoidFocalClassificationLoss() (cls_layers): Sequential( (0): Linear(in_features=640, out_features=256, bias=False) (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Linear(in_features=256, out_features=256, bias=False) (4): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() (6): Linear(in_features=256, out_features=1, bias=True) ) ) (roi_head): PVRCNNHead( (proposal_target_layer): ProposalTargetLayer() (reg_loss_func): WeightedSmoothL1Loss() (roi_grid_pool_layer): StackSAModuleMSG( (groupers): ModuleList( (0): QueryAndGroup() (1): QueryAndGroup() ) (mlps): ModuleList( (0): Sequential( (0): Conv2d(131, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) (1): Sequential( (0): Conv2d(131, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU() ) ) ) (shared_fc_layer): Sequential( (0): Conv1d(27648, 256, kernel_size=(1,), stride=(1,), bias=False) (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Dropout(p=0.3, inplace=False) (4): Conv1d(256, 256, kernel_size=(1,), stride=(1,), bias=False) (5): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (6): ReLU() ) (cls_layers): Sequential( (0): Conv1d(256, 256, kernel_size=(1,), stride=(1,), bias=False) (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Dropout(p=0.3, inplace=False) (4): Conv1d(256, 256, kernel_size=(1,), stride=(1,), bias=False) (5): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (6): ReLU() (7): Conv1d(256, 1, kernel_size=(1,), stride=(1,)) ) (reg_layers): Sequential( (0): Conv1d(256, 256, kernel_size=(1,), stride=(1,), bias=False) (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() (3): Dropout(p=0.3, inplace=False) (4): Conv1d(256, 256, kernel_size=(1,), stride=(1,), bias=False) (5): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (6): ReLU() (7): Conv1d(256, 7, kernel_size=(1,), stride=(1,)) ) ) ) 2022-02-23 09:30:30,579 INFO **Start training kitti_models/pv_rcnn(default)**

MartinHahner commented 2 years ago

Maybe it is related to these changes?

VsionQing commented 2 years ago

I downloaded the latest version, but I don't know how to use sh file to find TCP port under windows. How to solve it? And how to test whether the TCP port works

MartinHahner commented 2 years ago

Aha, maybe Windows is then the issue here. I am not sure if this codebase works on Windows at all.

VsionQing commented 2 years ago

Aha, maybe Windows is then the issue here. I am not sure if this codebase works on Windows at all.

I have a new guess. Is it possible that there is something wrong with my data set. In addition, how to check whether your TCP port is correct?

VsionQing commented 2 years ago

Aha, maybe Windows is then the issue here. I am not sure if this codebase works on Windows at all.

Then,i try to train the model pointpillar ,then i success. So,can you tell me the direct Bev detection method and PV with the following pointpillar_ What are the differences of RCNN? Or do you have any idea what is the most likely cause of training failure? In addition, I tested that pointrcnn can not run. I think it may be due to the configuration of 3dbackbone and so on

VsionQing commented 2 years ago

Aha, maybe Windows is then the issue here. I am not sure if this codebase works on Windows at all.

Deep Learning for 3D Point Clouds: A Survey Yulan Guo∗ , Hanyun Wang∗ , Qingyong Hu∗ , Hao Liu∗ , Li Liu, and Mohammed Bennamoun From this review, I read about the classification of target detection algorithms, namely Region Proposal-based Methods and Single Shot Methods .Some models in openpcdet cannot be trained for the former and can be trained for the latter. Do you have any clue?

github-actions[bot] commented 2 years ago

This issue is stale because it has been open for 30 days with no activity.

github-actions[bot] commented 2 years ago

This issue was closed because it has been inactive for 14 days since being marked as stale.