search

zyrant / SPGroup3D

[AAAI 2024] SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection
Other
35 stars 1 forks source link

Troubleshooting Superpoints Path Error in ScanNet Data Preparation #1

Closed linQian99 closed 6 months ago

linQian99 commented 7 months ago

Hi, thank you for your great work! I have a problem about preparing scannet data for superpoints. I firstly put Superpoints folder prepared scannet data and run following scripts to prepare datasets.

python batch_load_scannet_data_superpoint.py
python extract_posed_images.py
cd ../..
python tools/create_data.py scannet --root-path ./data/scannet --out-dir ./data/scannet --extra-tag scannet

The folder structure shows below. I think it should be correct. ├── batch_load_scannet_data.py ├── batch_load_scannet_data_superpoint.py ├── download-scannet.py ├── extract_posed_images.py ├── instance_mask ├── load_scannet_data.py ├── load_scannet_data_superpoint.py ├── meta_data ├── points ├── posed_images ├── pycache ├── README.md ├── scannet_infos_test.pkl ├── scannet_infos_train.pkl ├── scannet_infos_val.pkl ├── scannet_instance_data ├── scannet_utils.py ├── scans -> /media/lin/LinQ4T/Dataset/scannet/scans ├── scans_test -> /media/lin/LinQ4T/Dataset/scannet/scans_test ├── seg_info ├── semantic_mask ├── superpoints └── tasks -> /media/lin/LinQ4T/Dataset/scannet/tasks

The message shows the superpoints have some problems, could you please help me to see is the process of preparing the dataset incorrect? Thank you very much.

Error output:

(SP38) lin@aorus:/media/lin/LinQianROG/Ubuntu/SPGroup3D$ CUDA_VISIBLE_DEVICE=1 bash tools/dist_train.sh projects/configs/SPGroup_scannet.py 1 --work-dir work_dirs/
/home/lin/.conda/envs/SP38/lib/python3.8/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 from `os.environ['LOCAL_RANK']` instead. See 
https://pytorch.org/docs/stable/distributed.html#launch-utility for 
further instructions

  warnings.warn(
/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/MinkowskiEngine/__init__.py:36: UserWarning: The environment variable `OMP_NUM_THREADS` not set. MinkowskiEngine will automatically set `OMP_NUM_THREADS=16`. If you want to set `OMP_NUM_THREADS` manually, please export it on the command line before running a python script. e.g. `export OMP_NUM_THREADS=12; python your_program.py`. It is recommended to set it below 24.
  warnings.warn(
projects.spgroup
/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/mmdet/utils/setup_env.py:48: UserWarning: Setting MKL_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.
  warnings.warn(
2024-04-15 17:13:54,583 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.8.19 (default, Mar 20 2024, 19:58:24) [GCC 11.2.0]
CUDA available: True
GPU 0,1: NVIDIA GeForce RTX 3090
CUDA_HOME: /usr/local/cuda-11.7
NVCC: Cuda compilation tools, release 11.7, V11.7.64
GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 1.12.1+cu113
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.3
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
  - CuDNN 8.3.2  (built against CUDA 11.5)
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

TorchVision: 0.13.1+cu113
OpenCV: 4.9.0
MMCV: 1.6.0
MMCV Compiler: GCC 9.3
MMCV CUDA Compiler: 11.3
MMDetection: 2.24.0
MMSegmentation: 0.24.1
MMDetection3D: 1.0.0rc3+06f27c5
spconv2.0: True
------------------------------------------------------------

2024-04-15 17:13:55,523 - mmdet - INFO - Distributed training: True
2024-04-15 17:13:56,448 - mmdet - INFO - Config:
plugin = True
plugin_dir = 'projects/spgroup/'
voxel_size = 0.02
model = dict(
    type='SPMinkSingleStage3DDetector',
    voxel_size=0.02,
    backbone=dict(type='BiResNet', in_channels=3, out_channels=64),
    voxel_encoder=dict(
        type='SSG',
        in_channels=64,
        local_k=8,
        voxel_size=0.02,
        latter_voxel_size=0.04,
        feat_channels=(64, 128, 128),
        with_xyz=True,
        with_distance=False,
        with_cluster_center=False,
        with_superpoint_center=True,
        mode='max'),
    head=dict(
        type='SPHead',
        pred_layer_cfg=dict(
            in_channels=390,
            cls_linear_channels=(256, 256),
            reg_linear_channels=(256, 256),
            center_linear_channels=(256, 256)),
        norm_cfg=dict(type='LN', eps=0.001),
        n_reg_outs=6,
        n_classes=18,
        center_type='pow',
        pts_threshold=18,
        center_loss=dict(type='CrossEntropyLoss', use_sigmoid=True),
        bbox_loss=dict(type='AxisAlignedIoULoss', mode='diou'),
        cls_loss=dict(type='FocalLoss'),
        vote_loss=dict(type='SmoothL1Loss', beta=0.04, reduction='sum'),
        cls_cost=dict(type='FocalLossCost', weight=1),
        reg_cost=dict(type='IoU3DCost', iou_mode='diou', weight=1)),
    train_cfg=dict(),
    test_cfg=dict(nms_pre=1000, iou_thr=0.5, score_thr=0.01))
dataset_type = 'SPScanNetDataset'
data_root = './data/scannet/'
class_names = ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
               'bookshelf', 'picture', 'counter', 'desk', 'curtain',
               'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
               'garbagebin')
train_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        shift_height=False,
        use_color=True,
        load_dim=6,
        use_dim=[0, 1, 2, 3, 4, 5]),
    dict(type='LoadSuperPointsFromFile'),
    dict(
        type='LoadAnnotations3D',
        with_bbox_3d=True,
        with_label_3d=True,
        with_mask_3d=True,
        with_seg_3d=True),
    dict(type='GlobalAlignment', rotation_axis=2),
    dict(
        type='PointSegClassMapping',
        valid_cat_ids=(3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34,
                       36, 39)),
    dict(type='SPPointSample', num_points=0.33),
    dict(
        type='RandomFlip3D',
        sync_2d=False,
        flip_ratio_bev_horizontal=0.5,
        flip_ratio_bev_vertical=0.5),
    dict(
        type='GlobalRotScaleTrans',
        rot_range=[-0.02, 0.02],
        scale_ratio_range=[0.9, 1.1],
        translation_std=[0.1, 0.1, 0.1],
        shift_height=False),
    dict(type='NormalizePointsColor', color_mean=None),
    dict(
        type='SPDefaultFormatBundle3D',
        class_names=('cabinet', 'bed', 'chair', 'sofa', 'table', 'door',
                     'window', 'bookshelf', 'picture', 'counter', 'desk',
                     'curtain', 'refrigerator', 'showercurtrain', 'toilet',
                     'sink', 'bathtub', 'garbagebin')),
    dict(
        type='Collect3D',
        keys=[
            'points', 'superpoints', 'gt_bboxes_3d', 'gt_labels_3d',
            'pts_semantic_mask', 'pts_instance_mask'
        ])
]
test_pipeline = [
    dict(
        type='LoadPointsFromFile',
        coord_type='DEPTH',
        shift_height=False,
        use_color=True,
        load_dim=6,
        use_dim=[0, 1, 2, 3, 4, 5]),
    dict(type='LoadSuperPointsFromFile'),
    dict(type='GlobalAlignment', rotation_axis=2),
    dict(
        type='MultiScaleFlipAug3D',
        img_scale=(1333, 800),
        pts_scale_ratio=1,
        flip=False,
        transforms=[
            dict(type='NormalizePointsColor', color_mean=None),
            dict(
                type='SPDefaultFormatBundle3D',
                class_names=('cabinet', 'bed', 'chair', 'sofa', 'table',
                             'door', 'window', 'bookshelf', 'picture',
                             'counter', 'desk', 'curtain', 'refrigerator',
                             'showercurtrain', 'toilet', 'sink', 'bathtub',
                             'garbagebin'),
                with_label=False),
            dict(type='Collect3D', keys=['points', 'superpoints'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=4,
    train=dict(
        type='RepeatDataset',
        times=15,
        dataset=dict(
            type='SPScanNetDataset',
            data_root='./data/scannet/',
            ann_file='./data/scannet/scannet_infos_train.pkl',
            pipeline=[
                dict(
                    type='LoadPointsFromFile',
                    coord_type='DEPTH',
                    shift_height=False,
                    use_color=True,
                    load_dim=6,
                    use_dim=[0, 1, 2, 3, 4, 5]),
                dict(type='LoadSuperPointsFromFile'),
                dict(
                    type='LoadAnnotations3D',
                    with_bbox_3d=True,
                    with_label_3d=True,
                    with_mask_3d=True,
                    with_seg_3d=True),
                dict(type='GlobalAlignment', rotation_axis=2),
                dict(
                    type='PointSegClassMapping',
                    valid_cat_ids=(3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24,
                                   28, 33, 34, 36, 39)),
                dict(type='SPPointSample', num_points=0.33),
                dict(
                    type='RandomFlip3D',
                    sync_2d=False,
                    flip_ratio_bev_horizontal=0.5,
                    flip_ratio_bev_vertical=0.5),
                dict(
                    type='GlobalRotScaleTrans',
                    rot_range=[-0.02, 0.02],
                    scale_ratio_range=[0.9, 1.1],
                    translation_std=[0.1, 0.1, 0.1],
                    shift_height=False),
                dict(type='NormalizePointsColor', color_mean=None),
                dict(
                    type='SPDefaultFormatBundle3D',
                    class_names=('cabinet', 'bed', 'chair', 'sofa', 'table',
                                 'door', 'window', 'bookshelf', 'picture',
                                 'counter', 'desk', 'curtain', 'refrigerator',
                                 'showercurtrain', 'toilet', 'sink', 'bathtub',
                                 'garbagebin')),
                dict(
                    type='Collect3D',
                    keys=[
                        'points', 'superpoints', 'gt_bboxes_3d',
                        'gt_labels_3d', 'pts_semantic_mask',
                        'pts_instance_mask'
                    ])
            ],
            filter_empty_gt=True,
            classes=('cabinet', 'bed', 'chair', 'sofa', 'table', 'door',
                     'window', 'bookshelf', 'picture', 'counter', 'desk',
                     'curtain', 'refrigerator', 'showercurtrain', 'toilet',
                     'sink', 'bathtub', 'garbagebin'),
            box_type_3d='Depth')),
    val=dict(
        type='SPScanNetDataset',
        data_root='./data/scannet/',
        ann_file='./data/scannet/scannet_infos_val.pkl',
        pipeline=[
            dict(
                type='LoadPointsFromFile',
                coord_type='DEPTH',
                shift_height=False,
                use_color=True,
                load_dim=6,
                use_dim=[0, 1, 2, 3, 4, 5]),
            dict(type='LoadSuperPointsFromFile'),
            dict(type='GlobalAlignment', rotation_axis=2),
            dict(
                type='MultiScaleFlipAug3D',
                img_scale=(1333, 800),
                pts_scale_ratio=1,
                flip=False,
                transforms=[
                    dict(type='NormalizePointsColor', color_mean=None),
                    dict(
                        type='SPDefaultFormatBundle3D',
                        class_names=('cabinet', 'bed', 'chair', 'sofa',
                                     'table', 'door', 'window', 'bookshelf',
                                     'picture', 'counter', 'desk', 'curtain',
                                     'refrigerator', 'showercurtrain',
                                     'toilet', 'sink', 'bathtub',
                                     'garbagebin'),
                        with_label=False),
                    dict(type='Collect3D', keys=['points', 'superpoints'])
                ])
        ],
        classes=('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
                 'bookshelf', 'picture', 'counter', 'desk', 'curtain',
                 'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
                 'garbagebin'),
        test_mode=True,
        box_type_3d='Depth'),
    test=dict(
        type='SPScanNetDataset',
        data_root='./data/scannet/',
        ann_file='./data/scannet/scannet_infos_val.pkl',
        pipeline=[
            dict(
                type='LoadPointsFromFile',
                coord_type='DEPTH',
                shift_height=False,
                use_color=True,
                load_dim=6,
                use_dim=[0, 1, 2, 3, 4, 5]),
            dict(type='LoadSuperPointsFromFile'),
            dict(type='GlobalAlignment', rotation_axis=2),
            dict(
                type='MultiScaleFlipAug3D',
                img_scale=(1333, 800),
                pts_scale_ratio=1,
                flip=False,
                transforms=[
                    dict(type='NormalizePointsColor', color_mean=None),
                    dict(
                        type='SPDefaultFormatBundle3D',
                        class_names=('cabinet', 'bed', 'chair', 'sofa',
                                     'table', 'door', 'window', 'bookshelf',
                                     'picture', 'counter', 'desk', 'curtain',
                                     'refrigerator', 'showercurtrain',
                                     'toilet', 'sink', 'bathtub',
                                     'garbagebin'),
                        with_label=False),
                    dict(type='Collect3D', keys=['points', 'superpoints'])
                ])
        ],
        classes=('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
                 'bookshelf', 'picture', 'counter', 'desk', 'curtain',
                 'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
                 'garbagebin'),
        test_mode=True,
        box_type_3d='Depth'))
optimizer = dict(type='AdamW', lr=0.000125, weight_decay=1.25e-05)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[9, 12])
runner = dict(type='EpochBasedRunner', max_epochs=15)
custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
checkpoint_config = dict(interval=1, max_keep_ckpts=10)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = 'work_dirs/'
load_from = None
resume_from = None
workflow = [('train', 1)]
gpu_ids = range(0, 1)

2024-04-15 17:13:56,448 - mmdet - INFO - Set random seed to 0, deterministic: False
2024-04-15 17:13:56,638 - mmdet - INFO - Model:
SPMinkSingleStage3DDetector(
  (backbone): BiResNet(
    (conv1): Sequential(
      (0): MinkowskiConvolution(in=3, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
      (3): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      (4): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): MinkowskiReLU()
    )
    (relu): MinkowskiReLU()
    (layer1): Sequential(
      (0): BasicBlock(
        (conv1): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
        (downsample): Sequential(
          (0): MinkowskiConvolution(in=64, out=64, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=64, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
    )
    (layer2): Sequential(
      (0): BasicBlock(
        (conv1): MinkowskiConvolution(in=64, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
        (downsample): Sequential(
          (0): MinkowskiConvolution(in=64, out=128, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
    )
    (layer3): Sequential(
      (0): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
        (downsample): Sequential(
          (0): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
    )
    (layer4): Sequential(
      (0): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
        (downsample): Sequential(
          (0): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
    )
    (compression3): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (compression4): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (down3): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (down4): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
      (3): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
      (4): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (layer3_): Sequential(
      (0): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
      (1): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
    )
    (layer4_): Sequential(
      (0): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
      (1): BasicBlock(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
      )
    )
    (layer5_): Sequential(
      (0): Bottleneck(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm3): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
        (downsample): Sequential(
          (0): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (layer5): Sequential(
      (0): Bottleneck(
        (conv1): MinkowskiConvolution(in=128, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[2, 2, 2], dilation=[1, 1, 1])
        (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (norm3): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): MinkowskiReLU()
        (downsample): Sequential(
          (0): MinkowskiConvolution(in=128, out=256, kernel_size=[1, 1, 1], stride=[2, 2, 2], dilation=[1, 1, 1])
          (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (spp): DAPPM(
      (scale1): Sequential(
        (0): MinkowskiAvgPooling(kernel_size=[5, 5, 5], stride=[2, 2, 2], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=256, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (scale2): Sequential(
        (0): MinkowskiAvgPooling(kernel_size=[9, 9, 9], stride=[4, 4, 4], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=256, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (scale3): Sequential(
        (0): MinkowskiAvgPooling(kernel_size=[17, 17, 17], stride=[8, 8, 8], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=256, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (scale4): Sequential(
        (0): MinkowskiAvgPooling(kernel_size=[33, 33, 33], stride=[16, 16, 16], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiReLU()
        (3): MinkowskiConvolution(in=256, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (scale0): Sequential(
        (0): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=256, out=128, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (process1): Sequential(
        (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (process2): Sequential(
        (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (process3): Sequential(
        (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (process4): Sequential(
        (0): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (compression): Sequential(
        (0): MinkowskiBatchNorm(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=640, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
      (shortcut): Sequential(
        (0): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (1): MinkowskiReLU()
        (2): MinkowskiConvolution(in=256, out=256, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      )
    )
    (out): Sequential(
      (0): MinkowskiConvolutionTranspose(in=256, out=256, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
      (3): MinkowskiConvolution(in=256, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (4): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): MinkowskiReLU()
    )
  )
  (head): SPHead(
    (center_loss): CrossEntropyLoss(avg_non_ignore=False)
    (bbox_loss): AxisAlignedIoULoss()
    (cls_loss): FocalLoss()
    (vote_loss): SmoothL1Loss()
    (conv_center): Sequential(
      (0): Linear(in_features=390, out_features=256, bias=False)
      (1): LayerNorm((256,), eps=0.001, elementwise_affine=True)
      (2): ReLU(inplace=True)
      (3): Linear(in_features=256, out_features=256, bias=False)
      (4): LayerNorm((256,), eps=0.001, elementwise_affine=True)
      (5): ReLU(inplace=True)
      (6): Linear(in_features=256, out_features=1, bias=True)
    )
    (conv_reg): Sequential(
      (0): Linear(in_features=390, out_features=256, bias=False)
      (1): LayerNorm((256,), eps=0.001, elementwise_affine=True)
      (2): ReLU(inplace=True)
      (3): Linear(in_features=256, out_features=256, bias=False)
      (4): LayerNorm((256,), eps=0.001, elementwise_affine=True)
      (5): ReLU(inplace=True)
      (6): Linear(in_features=256, out_features=6, bias=True)
    )
    (conv_cls): Sequential(
      (0): Linear(in_features=390, out_features=256, bias=False)
      (1): LayerNorm((256,), eps=0.001, elementwise_affine=True)
      (2): ReLU(inplace=True)
      (3): Linear(in_features=256, out_features=256, bias=False)
      (4): LayerNorm((256,), eps=0.001, elementwise_affine=True)
      (5): ReLU(inplace=True)
      (6): Linear(in_features=256, out_features=18, bias=True)
    )
  )
  (voxel_encoder): SSG(
    (offset_block): Sequential(
      (0): MinkowskiConvolution(in=64, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiELU()
      (3): MinkowskiConvolution(in=64, out=64, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
      (4): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): MinkowskiELU()
      (6): MinkowskiConvolution(in=64, out=67, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
    )
    (ffn_layers): ModuleList(
      (0): Sequential(
        (0): MinkowskiConvolution(in=140, out=64, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[3, 3, 3])
        (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiELU()
      )
      (1): Sequential(
        (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[3, 3, 3])
        (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiELU()
      )
      (2): Sequential(
        (0): MinkowskiConvolution(in=256, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[3, 3, 3])
        (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): MinkowskiELU()
      )
    )
    (attn_layers): ModuleList(
      (0): SuperpointAttention_v2(
        (feature_transform): Linear(in_features=70, out_features=70, bias=True)
        (coord_linear): Linear(in_features=3, out_features=70, bias=True)
        (feat_linear): Linear(in_features=70, out_features=70, bias=True)
        (softmax): Softmax(dim=1)
        (norm): LayerNorm((70,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (1): SuperpointAttention_v2(
        (feature_transform): Linear(in_features=64, out_features=64, bias=True)
        (coord_linear): Linear(in_features=3, out_features=64, bias=True)
        (feat_linear): Linear(in_features=64, out_features=64, bias=True)
        (softmax): Softmax(dim=1)
        (norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (2): SuperpointAttention_v2(
        (feature_transform): Linear(in_features=128, out_features=128, bias=True)
        (coord_linear): Linear(in_features=3, out_features=128, bias=True)
        (feat_linear): Linear(in_features=128, out_features=128, bias=True)
        (softmax): Softmax(dim=1)
        (norm): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (3): SuperpointAttention_v2(
        (feature_transform): Linear(in_features=128, out_features=128, bias=True)
        (coord_linear): Linear(in_features=3, out_features=128, bias=True)
        (feat_linear): Linear(in_features=128, out_features=128, bias=True)
        (softmax): Softmax(dim=1)
        (norm): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
    )
    (out_linear): Sequential(
      (0): Linear(in_features=390, out_features=390, bias=False)
      (1): LayerNorm((390,), eps=1e-05, elementwise_affine=True)
      (2): ELU(alpha=1.0)
      (3): Linear(in_features=390, out_features=390, bias=False)
      (4): LayerNorm((390,), eps=1e-05, elementwise_affine=True)
      (5): ELU(alpha=1.0)
    )
  )
)
2024-04-15 17:13:59,992 - mmdet - INFO - Start running, host: lin@aorus, work_dir: /media/lin/LinQianROG/Ubuntu/SPGroup3D/work_dirs
2024-04-15 17:13:59,992 - mmdet - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) StepLrUpdaterHook                  
(NORMAL      ) CheckpointHook                     
(LOW         ) DistEvalHook                       
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) StepLrUpdaterHook                  
(NORMAL      ) EmptyCacheHook                     
(NORMAL      ) DistSamplerSeedHook                
(LOW         ) IterTimerHook                      
(LOW         ) DistEvalHook                       
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_train_iter:
(VERY_HIGH   ) StepLrUpdaterHook                  
(LOW         ) IterTimerHook                      
(LOW         ) DistEvalHook                       
 -------------------- 
after_train_iter:
(ABOVE_NORMAL) OptimizerHook                      
(NORMAL      ) CheckpointHook                     
(NORMAL      ) EmptyCacheHook                     
(LOW         ) IterTimerHook                      
(LOW         ) DistEvalHook                       
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) CheckpointHook                     
(NORMAL      ) EmptyCacheHook                     
(LOW         ) DistEvalHook                       
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_val_epoch:
(NORMAL      ) EmptyCacheHook                     
(NORMAL      ) DistSamplerSeedHook                
(LOW         ) IterTimerHook                      
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_val_iter:
(LOW         ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) EmptyCacheHook                     
(LOW         ) IterTimerHook                      
 -------------------- 
after_val_epoch:
(NORMAL      ) EmptyCacheHook                     
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
after_run:
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
2024-04-15 17:13:59,992 - mmdet - INFO - workflow: [('train', 1)], max: 15 epochs
2024-04-15 17:13:59,992 - mmdet - INFO - Checkpoints will be saved to /media/lin/LinQianROG/Ubuntu/SPGroup3D/work_dirs by HardDiskBackend.
No superpoints path for sample scene0052_02
No superpoints path for sample scene0450_00
No superpoints path for sample scene0322_00
No superpoints path for sample scene0134_02
No superpoints path for sample scene0630_03No superpoints path for sample scene0628_00

No superpoints path for sample scene0452_00
No superpoints path for sample scene0548_01
Traceback (most recent call last):
  File "tools/train.py", line 291, in <module>
No superpoints path for sample scene0623_01
    main()
  File "tools/train.py", line 280, in main
    train_model(
  File "/media/lin/LinQianROG/Ubuntu/SPGroup3D/mmdet3d/apis/train.py", line 344, in train_model
    train_detector(
  File "/media/lin/LinQianROG/Ubuntu/SPGroup3D/mmdet3d/apis/train.py", line 319, in train_detector
    runner.run(data_loaders, cfg.workflow)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 49, in train
    for i, data_batch in enumerate(self.data_loader):
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 681, in __next__
    data = self._next_data()
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1376, in _next_data
    return self._process_data(data)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1402, in _process_data
    data.reraise()
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/_utils.py", line 461, in reraise
    raise exception
UnboundLocalError: Caught UnboundLocalError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/mmdet/datasets/dataset_wrappers.py", line 178, in __getitem__
    return self.dataset[idx % self._ori_len]
  File "/media/lin/LinQianROG/Ubuntu/SPGroup3D/mmdet3d/datasets/custom_3d.py", line 435, in __getitem__
    data = self.prepare_train_data(idx)
  File "/media/lin/LinQianROG/Ubuntu/SPGroup3D/projects/spgroup/scannet_dataset.py", line 173, in prepare_train_data
    input_dict = self.get_data_info(index)
  File "/media/lin/LinQianROG/Ubuntu/SPGroup3D/projects/spgroup/scannet_dataset.py", line 149, in get_data_info
    print(f"Superpoints path for sample {sample_idx}: {superpoints_filename}")
UnboundLocalError: local variable 'superpoints_filename' referenced before assignment

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 3810230) of binary: /home/lin/.conda/envs/SP38/bin/python
Traceback (most recent call last):
  File "/home/lin/.conda/envs/SP38/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/lin/.conda/envs/SP38/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/distributed/launch.py", line 193, in <module>
    main()
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/distributed/launch.py", line 189, in main
    launch(args)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/distributed/launch.py", line 174, in launch
    run(args)
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/distributed/run.py", line 752, in run
    elastic_launch(
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 131, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/home/lin/.conda/envs/SP38/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 245, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
============================================================
tools/train.py FAILED
------------------------------------------------------------
Failures:
  <NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2024-04-15_17:14:05
  host      : aorus
  rank      : 0 (local_rank: 0)
  exitcode  : 1 (pid: 3810230)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
zyrant commented 7 months ago

hi, It seems that your pkl file is not generated correctly and does not containsuperpoints_filename. please check https://github.com/zyrant/SPGroup3D/blob/d6ee2ddb9c674609a0dd66026f395d246c3899ad/tools/data_converter/scannet_data_utils.py#L118 to https://github.com/zyrant/SPGroup3D/blob/d6ee2ddb9c674609a0dd66026f395d246c3899ad/tools/data_converter/scannet_data_utils.py#L126, which are used to generate pts_superpoints_path.

the file in pkl should like this 

{'point_cloud': {'num_features': 6, 'lidar_idx': 'scene0191_00'}, 
'pts_path': 'points/scene0191_00.bin', 
'pts_superpoints_path': 'superpoints/scene0191_00.bin', 
'pts_instance_mask_path': 'instance_mask/scene0191_00.bin', 
'pts_semantic_mask_path': 'semantic_mask/scene0191_00.bin', 
'annos': {'gt_num': 7, 'name': array(['door', 'table', 'window', 'garbagebin', 'chair', 'window',
       'window'], dtype='<U10'), 'location': array([[ 1.9491133 ,  2.5492249 ,  1.07194896],....
zyrant commented 7 months ago

I will update Readme soon and upload my pkl file.

linQian99 commented 7 months ago

Thank you for your detailed explanation and patience! I see, it should be because of the process of creating pkl files. I tried to create pkl files with two different environment. The first one for TR3D could create but second env for SPgroup3D will show following errors:

(SP38) lin@aorus:/media/lin/LinQianROG/Ubuntu/SPGroup3D$ python tools/create_data.py scannet --root-path ./data/scannet --out-dir ./data/scannet --extra-tag scannetc Traceback (most recent call last): File "tools/create_data.py", line 5, in <module> from tools.data_converter import indoor_converter as indoor File "/media/lin/LinQianROG/Ubuntu/SPGroup3D/tools/data_converter/indoor_converter.py", line 9, in <module> from tools.data_converter.scannet_md40_data_utils import ScanNetData_md40, ScanNetSegData_md40 ModuleNotFoundError: No module named 'tools.data_converter.scannet_md40_data_utils'

It seems that data_converter folder is lack of scannet_md40_data_utils.py which is shown below.

image

zyrant commented 6 months ago

hi

Ops. This was a mistake when I cleaned up the code. You just need to comment on the code related to scannet_md40.

best wishes.

linQian99 commented 6 months ago

Thank you for your reply! Now it works.

Best Regards