Closed suvasis closed 1 year ago
2022-09-23 10:21:21,551 INFO Start training kitti_models/pv_rcnn(default)
epochs: 0it [00:07, ?it/s]
2022-09-23 10:21:30,211 INFO End training kitti_models/pv_rcnn(default)
As shown in your log, the training has been finished in previous lauch.
hi,
After I followed this comment https://github.com/open-mmlab/OpenPCDet/issues/938
#if mp.get_start_method(allow_none=True) is None:
# mp.set_start_method('spawn')
The training worked only for batch_size 2. If I increase the batch_size to 4 or beyond (the log snippet is attached below). What should I do to fix this?
For batch_size=2, the run the successful. For batch_size=4, the training fails.
///////////////////////////////////////////////////////////////////////////////////////////
batch_size=2
///////////////////////////////////////////////////////////////////////////////////////////
command: (pytorchbuild) minasm@lambda-quad:~/suvasis/tools/pvrcnn/OpenPCDet/tools$ ./scripts/dist_train.sh 2 --batch_size 2 --epochs 10 --cfg_file cfgs/kitti_models/pv_rcnn.yaml
log: Cyclist AP@0.50, 0.25, 0.25: bbox AP:90.7043, 78.4946, 74.1905 bev AP:90.0927, 74.9485, 70.5419 3d AP:90.0911, 74.9443, 70.5419 aos AP:90.47, 76.53, 72.11 Cyclist AP_R40@0.50, 0.25, 0.25: bbox AP:94.0771, 79.2091, 75.3161 bev AP:93.6473, 75.5676, 72.0880 3d AP:93.6469, 75.5664, 72.0693 aos AP:93.83, 77.14, 73.01
2022-09-23 14:07:09,004 INFO Result is save to /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/default/eval/eval_with_train/epoch_10/val 2022-09-23 14:07:09,005 INFO ****Evaluation done.***** 2022-09-23 14:07:09,026 INFO Epoch 10 has been evaluated Wait 30 seconds for next check (progress: 0.0 / 0 minutes): /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/defaul2022-09-23 14:07:39,058 INFO **End evaluation kitti_models/pv_rcnn(default)** ///////////////////////////////////////////////////////////////////////////////////////////
batch_size=4
///////////////////////////////////////////////////////////////////////////////////////////
command: OpenPCDet/tools$ ./scripts/dist_train.sh 2 --batch_size 4 --epochs 10 --cfg_file cfgs/kitti_models/pv_rcnn.yaml
Log:
Failures:
This issue is stale because it has been open for 30 days with no activity.
hi,
I have 2 gpu machine. Single GPU training works ok. However for 2 gpus, It seems to be waiting for something for ever. The GPU utilization is 0% for both GPUs.
I am using Kitti dataset as described in the documentation.
The command as shown:
OpenPCDet/tools$ ./scripts/dist_train.sh 2 --batch_size 2 --epochs 1 --cfg_file cfgs/kitti_models/pv_rcnn.yaml
My code base is as of Sep 22, 2022.
Log snippet:
2022-09-23 10:21:21,551 INFO **Start training kitti_models/pv_rcnn(default)** epochs: 0it [00:07, ?it/s] 2022-09-23 10:21:30,211 INFO **End training kitti_models/pv_rcnn(default)**
2022-09-23 10:21:30,212 INFO **Start evaluation kitti_models/pv_rcnn(default)** 2022-09-23 10:21:30,213 INFO Loading KITTI dataset 2022-09-23 10:21:30,304 INFO Total samples for KITTI dataset: 3769 Wait 30 seconds for next check (progress: 0.0 / 0 minutes): /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/default/ckpt
LOG SNIPPET:
NGPUS=2
python -m torch.distributed.launch --nproc_per_node=2 --rdzv_endpoint=localhost:27915 train.py --launcher pytorch --batch_size 2 --epochs 1 --cfg_file cfgs/kitti_models/pv_rcnn.yaml /home/minasm/suvasis/tools/anaconda3/envs/pytorchbuild/lib/python3.9/site-packages/torch/distributed/launch.py:178: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set by default in torchrun. If your script expects
--local_rank
argument to be set, please change it to read fromos.environ['LOCAL_RANK']
instead. See https://pytorch.org/docs/stable/distributed.html#launch-utility for further instructionswarnings.warn( WARNING:torch.distributed.run:
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
2022-09-23 10:21:20,169 INFO **Start logging** 2022-09-23 10:21:20,169 INFO CUDA_VISIBLE_DEVICES=ALL 2022-09-23 10:21:20,169 INFO total_batch_size: 2 2022-09-23 10:21:20,169 INFO cfg_file cfgs/kitti_models/pv_rcnn.yaml 2022-09-23 10:21:20,169 INFO batch_size 1 2022-09-23 10:21:20,170 INFO epochs 1 2022-09-23 10:21:20,170 INFO workers 4 2022-09-23 10:21:20,170 INFO extra_tag default 2022-09-23 10:21:20,170 INFO ckpt None 2022-09-23 10:21:20,170 INFO pretrained_model None 2022-09-23 10:21:20,170 INFO launcher pytorch 2022-09-23 10:21:20,170 INFO tcp_port 18888 2022-09-23 10:21:20,170 INFO sync_bn False 2022-09-23 10:21:20,170 INFO fix_random_seed False 2022-09-23 10:21:20,170 INFO ckpt_save_interval 1 2022-09-23 10:21:20,170 INFO local_rank 0 2022-09-23 10:21:20,170 INFO max_ckpt_save_num 30 2022-09-23 10:21:20,170 INFO merge_all_iters_to_one_epoch False 2022-09-23 10:21:20,170 INFO set_cfgs None 2022-09-23 10:21:20,170 INFO max_waiting_mins 0 2022-09-23 10:21:20,170 INFO start_epoch 0 2022-09-23 10:21:20,170 INFO num_epochs_to_eval 0 2022-09-23 10:21:20,170 INFO save_to_file False 2022-09-23 10:21:20,170 INFO use_tqdm_to_record False 2022-09-23 10:21:20,170 INFO logger_iter_interval 50 2022-09-23 10:21:20,170 INFO ckpt_save_time_interval 300 2022-09-23 10:21:20,170 INFO wo_gpu_stat False 2022-09-23 10:21:20,170 INFO cfg.ROOT_DIR: /home/minasm/suvasis/tools/pvrcnn/OpenPCDet 2022-09-23 10:21:20,170 INFO cfg.LOCAL_RANK: 0 2022-09-23 10:21:20,170 INFO cfg.CLASS_NAMES: ['Car', 'Pedestrian', 'Cyclist'] 2022-09-23 10:21:20,170 INFO cfg.DATA_CONFIG = edict() 2022-09-23 10:21:20,170 INFO cfg.DATA_CONFIG.DATASET: KittiDataset 2022-09-23 10:21:20,170 INFO cfg.DATA_CONFIG.DATA_PATH: ../data/kitti 2022-09-23 10:21:20,170 INFO cfg.DATA_CONFIG.POINT_CLOUD_RANGE: [0, -40, -3, 70.4, 40, 1] 2022-09-23 10:21:20,170 INFO cfg.DATA_CONFIG.DATA_SPLIT = edict() 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.DATA_SPLIT.train: train 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.DATA_SPLIT.test: val 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.INFO_PATH = edict() 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.INFO_PATH.train: ['kitti_infos_train.pkl'] 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.INFO_PATH.test: ['kitti_infos_val.pkl'] 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.GET_ITEM_LIST: ['points'] 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.FOV_POINTS_ONLY: True 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.DATA_AUGMENTOR = edict() 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.DATA_AUGMENTOR.DISABLE_AUG_LIST: ['placeholder'] 2022-09-23 10:21:20,171 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: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]}] 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING = edict() 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.encoding_type: absolute_coordinates_encoding 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.used_feature_list: ['x', 'y', 'z', 'intensity'] 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG.POINT_FEATURE_ENCODING.src_feature_list: ['x', 'y', 'z', 'intensity'] 2022-09-23 10:21:20,171 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}}] 2022-09-23 10:21:20,171 INFO cfg.DATA_CONFIG._BASECONFIG: cfgs/dataset_configs/kitti_dataset.yaml 2022-09-23 10:21:20,171 INFO cfg.MODEL = edict() 2022-09-23 10:21:20,171 INFO cfg.MODEL.NAME: PVRCNN 2022-09-23 10:21:20,171 INFO cfg.MODEL.VFE = edict() 2022-09-23 10:21:20,171 INFO cfg.MODEL.VFE.NAME: MeanVFE 2022-09-23 10:21:20,171 INFO cfg.MODEL.BACKBONE_3D = edict() 2022-09-23 10:21:20,171 INFO cfg.MODEL.BACKBONE_3D.NAME: VoxelBackBone8x 2022-09-23 10:21:20,171 INFO cfg.MODEL.MAP_TO_BEV = edict() 2022-09-23 10:21:20,171 INFO cfg.MODEL.MAP_TO_BEV.NAME: HeightCompression 2022-09-23 10:21:20,171 INFO cfg.MODEL.MAP_TO_BEV.NUM_BEV_FEATURES: 256 2022-09-23 10:21:20,171 INFO cfg.MODEL.BACKBONE_2D = edict() 2022-09-23 10:21:20,171 INFO cfg.MODEL.BACKBONE_2D.NAME: BaseBEVBackbone 2022-09-23 10:21:20,171 INFO cfg.MODEL.BACKBONE_2D.LAYER_NUMS: [5, 5] 2022-09-23 10:21:20,172 INFO cfg.MODEL.BACKBONE_2D.LAYER_STRIDES: [1, 2] 2022-09-23 10:21:20,172 INFO cfg.MODEL.BACKBONE_2D.NUM_FILTERS: [128, 256] 2022-09-23 10:21:20,172 INFO cfg.MODEL.BACKBONE_2D.UPSAMPLE_STRIDES: [1, 2] 2022-09-23 10:21:20,172 INFO cfg.MODEL.BACKBONE_2D.NUM_UPSAMPLE_FILTERS: [256, 256] 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD = edict() 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.NAME: AnchorHeadSingle 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.CLASS_AGNOSTIC: False 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.USE_DIRECTION_CLASSIFIER: True 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.DIR_OFFSET: 0.78539 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.DIR_LIMIT_OFFSET: 0.0 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.NUM_DIR_BINS: 2 2022-09-23 10:21:20,172 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}] 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG = edict() 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.NAME: AxisAlignedTargetAssigner 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.POS_FRACTION: -1.0 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.SAMPLE_SIZE: 512 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.NORM_BY_NUM_EXAMPLES: False 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.MATCH_HEIGHT: False 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.TARGET_ASSIGNER_CONFIG.BOX_CODER: ResidualCoder 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG = edict() 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.cls_weight: 1.0 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.loc_weight: 2.0 2022-09-23 10:21:20,172 INFO cfg.MODEL.DENSE_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.dir_weight: 0.2 2022-09-23 10:21:20,172 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] 2022-09-23 10:21:20,172 INFO cfg.MODEL.PFE = edict() 2022-09-23 10:21:20,172 INFO cfg.MODEL.PFE.NAME: VoxelSetAbstraction 2022-09-23 10:21:20,172 INFO cfg.MODEL.PFE.POINT_SOURCE: raw_points 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.NUM_KEYPOINTS: 2048 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.NUM_OUTPUT_FEATURES: 128 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SAMPLE_METHOD: FPS 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.FEATURES_SOURCE: ['bev', 'x_conv1', 'x_conv2', 'x_conv3', 'x_conv4', 'raw_points'] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER = edict() 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.raw_points = edict() 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.raw_points.MLPS: [[16, 16], [16, 16]] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.raw_points.POOL_RADIUS: [0.4, 0.8] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.raw_points.NSAMPLE: [16, 16] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1 = edict() 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.DOWNSAMPLE_FACTOR: 1 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.MLPS: [[16, 16], [16, 16]] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.POOL_RADIUS: [0.4, 0.8] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv1.NSAMPLE: [16, 16] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2 = edict() 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.DOWNSAMPLE_FACTOR: 2 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.MLPS: [[32, 32], [32, 32]] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.POOL_RADIUS: [0.8, 1.2] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv2.NSAMPLE: [16, 32] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3 = edict() 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.DOWNSAMPLE_FACTOR: 4 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.MLPS: [[64, 64], [64, 64]] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.POOL_RADIUS: [1.2, 2.4] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv3.NSAMPLE: [16, 32] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4 = edict() 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.DOWNSAMPLE_FACTOR: 8 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.MLPS: [[64, 64], [64, 64]] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.POOL_RADIUS: [2.4, 4.8] 2022-09-23 10:21:20,173 INFO cfg.MODEL.PFE.SA_LAYER.x_conv4.NSAMPLE: [16, 32] 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.NAME: PointHeadSimple 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.CLS_FC: [256, 256] 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.CLASS_AGNOSTIC: True 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.USE_POINT_FEATURES_BEFORE_FUSION: True 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.TARGET_CONFIG = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.TARGET_CONFIG.GT_EXTRA_WIDTH: [0.2, 0.2, 0.2] 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.LOSS_CONFIG = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.LOSS_CONFIG.LOSS_REG: smooth-l1 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.POINT_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.point_cls_weight: 1.0 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NAME: PVRCNNHead 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.CLASS_AGNOSTIC: True 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.SHARED_FC: [256, 256] 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.CLS_FC: [256, 256] 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.REG_FC: [256, 256] 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.DP_RATIO: 0.3 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_TYPE: nms_gpu 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.MULTI_CLASSES_NMS: False 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_PRE_MAXSIZE: 9000 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_POST_MAXSIZE: 512 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TRAIN.NMS_THRESH: 0.8 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST = edict() 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_TYPE: nms_gpu 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.MULTI_CLASSES_NMS: False 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_PRE_MAXSIZE: 1024 2022-09-23 10:21:20,174 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_POST_MAXSIZE: 100 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.NMS_CONFIG.TEST.NMS_THRESH: 0.7 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL = edict() 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.GRID_SIZE: 6 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.MLPS: [[64, 64], [64, 64]] 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.POOL_RADIUS: [0.8, 1.6] 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.NSAMPLE: [16, 16] 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.ROI_GRID_POOL.POOL_METHOD: max_pool 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG = edict() 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.BOX_CODER: ResidualCoder 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.ROI_PER_IMAGE: 128 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.FG_RATIO: 0.5 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.SAMPLE_ROI_BY_EACH_CLASS: True 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_SCORE_TYPE: roi_iou 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_FG_THRESH: 0.75 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_BG_THRESH: 0.25 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.CLS_BG_THRESH_LO: 0.1 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.HARD_BG_RATIO: 0.8 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.TARGET_CONFIG.REG_FG_THRESH: 0.55 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG = edict() 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.CLS_LOSS: BinaryCrossEntropy 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.REG_LOSS: smooth-l1 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.CORNER_LOSS_REGULARIZATION: True 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS = edict() 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.rcnn_cls_weight: 1.0 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.rcnn_reg_weight: 1.0 2022-09-23 10:21:20,175 INFO cfg.MODEL.ROI_HEAD.LOSS_CONFIG.LOSS_WEIGHTS.rcnn_corner_weight: 1.0 2022-09-23 10:21:20,175 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] 2022-09-23 10:21:20,175 INFO cfg.MODEL.POST_PROCESSING = edict() 2022-09-23 10:21:20,175 INFO cfg.MODEL.POST_PROCESSING.RECALL_THRESH_LIST: [0.3, 0.5, 0.7] 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.SCORE_THRESH: 0.1 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.OUTPUT_RAW_SCORE: False 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.EVAL_METRIC: kitti 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG = edict() 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.MULTI_CLASSES_NMS: False 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_TYPE: nms_gpu 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_THRESH: 0.1 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_PRE_MAXSIZE: 4096 2022-09-23 10:21:20,176 INFO cfg.MODEL.POST_PROCESSING.NMS_CONFIG.NMS_POST_MAXSIZE: 500 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION = edict() 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.BATCH_SIZE_PER_GPU: 2 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.NUM_EPOCHS: 80 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.OPTIMIZER: adam_onecycle 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.LR: 0.01 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.WEIGHT_DECAY: 0.01 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.MOMENTUM: 0.9 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.MOMS: [0.95, 0.85] 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.PCT_START: 0.4 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.DIV_FACTOR: 10 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.DECAY_STEP_LIST: [35, 45] 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.LR_DECAY: 0.1 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.LR_CLIP: 1e-07 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.LR_WARMUP: False 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.WARMUP_EPOCH: 1 2022-09-23 10:21:20,176 INFO cfg.OPTIMIZATION.GRAD_NORM_CLIP: 10 2022-09-23 10:21:20,176 INFO cfg.TAG: pv_rcnn 2022-09-23 10:21:20,176 INFO cfg.EXP_GROUP_PATH: kitti_models 2022-09-23 10:21:20,273 INFO Database filter by min points Car: 14357 => 13532 2022-09-23 10:21:20,273 INFO Database filter by min points Pedestrian: 2207 => 2168 2022-09-23 10:21:20,273 INFO Database filter by min points Cyclist: 734 => 705 2022-09-23 10:21:20,289 INFO Database filter by difficulty Car: 13532 => 10759 2022-09-23 10:21:20,291 INFO Database filter by difficulty Pedestrian: 2168 => 2075 2022-09-23 10:21:20,292 INFO Database filter by difficulty Cyclist: 705 => 581 2022-09-23 10:21:20,296 INFO Loading KITTI dataset 2022-09-23 10:21:20,370 INFO Total samples for KITTI dataset: 3712 /home/minasm/suvasis/tools/anaconda3/envs/pytorchbuild/lib/python3.9/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1659484806139/work/aten/src/ATen/native/TensorShape.cpp:2894.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] /home/minasm/suvasis/tools/anaconda3/envs/pytorchbuild/lib/python3.9/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1659484806139/work/aten/src/ATen/native/TensorShape.cpp:2894.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] 2022-09-23 10:21:21,303 INFO ==> Loading parameters from checkpoint /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/default/ckpt/checkpoint_epoch_2.pth to CPU 2022-09-23 10:21:21,413 INFO ==> Loading optimizer parameters from checkpoint /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/default/ckpt/checkpoint_epoch_2.pth to CPU ==> Checkpoint trained from version: pcdet+0.6.0+b61049f 2022-09-23 10:21:21,495 INFO ==> Done ==> Checkpoint trained from version: pcdet+0.6.0+b61049f 2022-09-23 10:21:21,548 INFO DistributedDataParallel( (module): 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((1, 1, 1, 1)) (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((1, 1, 1, 1)) (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,)) ) ) ) ) 2022-09-23 10:21:21,551 INFO **Start training kitti_models/pv_rcnn(default)** epochs: 0it [00:07, ?it/s] 2022-09-23 10:21:30,211 INFO **End training kitti_models/pv_rcnn(default)**
2022-09-23 10:21:30,212 INFO **Start evaluation kitti_models/pv_rcnn(default)** 2022-09-23 10:21:30,213 INFO Loading KITTI dataset 2022-09-23 10:21:30,304 INFO Total samples for KITTI dataset: 3769 Wait 30 seconds for next check (progress: 0.0 / 0 minutes): /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/defaulWait 30 seconds for next check (progress: 0.5 / 0 minutes): /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/defaulWait 30 seconds for next check (progress: 1.0 / 0 minutes): /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/defaulWait 30 seconds for next check (progress: 1.5 / 0 minutes): /home/minasm/suvasis/tools/pvrcnn/OpenPCDet/output/kitti_models/pv_rcnn/defaul