search

SamsungLabs / tr3d

[ICIP2023] TR3D: Towards Real-Time Indoor 3D Object Detection
Other
141 stars 8 forks source link

KeyError in DataLoader for training ScanNet in the Docker #19

Closed ChihaoZhang closed 8 months ago

ChihaoZhang commented 8 months ago

Hi, Dr. @filaPro, thanks for your works on 3D object detection. Since I cannot compile Minkowski Engine successfully on my computer (sadly the specific reason has not been figured out yet for now :disappointed:), I turned to docker for test. But when I tried it on ScanNet (using command python tools/train.py configs/tr3d/tr3d_scannet-3d-18class.py inside the container), the above mentioned error occurred, the detail output is

/opt/conda/lib/python3.7/site-packages/mmdet/utils/setup_env.py:39: UserWarning: 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.
  f'Setting OMP_NUM_THREADS environment variable for each process '
/opt/conda/lib/python3.7/site-packages/mmdet/utils/setup_env.py:49: 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.
  f'Setting MKL_NUM_THREADS environment variable for each process '
2023-12-25 01:48:11,477 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0]
CUDA available: True
GPU 0: NVIDIA GeForce RTX 2080 Ti
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.3, V11.3.109
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.12.1
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 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_61,code=sm_61;-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;-gencode;arch=compute_37,code=compute_37
  - 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
OpenCV: 4.8.1
MMCV: 1.6.0
MMCV Compiler: GCC 9.3
MMCV CUDA Compiler: 11.3
MMDetection: 2.24.1
MMSegmentation: 0.24.1
MMDetection3D: 1.0.0rc3+fa82f45
spconv2.0: False
------------------------------------------------------------

2023-12-25 01:48:12,197 - mmdet - INFO - Distributed training: False
2023-12-25 01:48:12,907 - mmdet - INFO - Config:
voxel_size = 0.01
n_points = 100000
model = dict(
    type='MinkSingleStage3DDetector',
    voxel_size=0.01,
    backbone=dict(
        type='MinkResNet',
        in_channels=3,
        max_channels=128,
        depth=34,
        norm='batch'),
    neck=dict(
        type='TR3DNeck', in_channels=(64, 128, 128, 128), out_channels=128),
    head=dict(
        type='TR3DHead',
        in_channels=128,
        n_reg_outs=6,
        n_classes=18,
        voxel_size=0.01,
        assigner=dict(
            type='TR3DAssigner',
            top_pts_threshold=6,
            label2level=[0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1,
                         0]),
        bbox_loss=dict(
            type='AxisAlignedIoULoss', mode='diou', reduction='none')),
    train_cfg=dict(),
    test_cfg=dict(nms_pre=1000, iou_thr=0.5, score_thr=0.01))
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
checkpoint_config = dict(interval=1, max_keep_ckpts=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/tr3d_scannet-3d-18class'
load_from = None
resume_from = None
workflow = [('train', 1)]
dataset_type = 'ScanNetDataset'
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='LoadAnnotations3D'),
    dict(type='GlobalAlignment', rotation_axis=2),
    dict(type='PointSample', 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='DefaultFormatBundle3D',
        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', 'gt_bboxes_3d', 'gt_labels_3d'])
]
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='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='DefaultFormatBundle3D',
                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'])
        ])
]
data = dict(
    samples_per_gpu=16,
    workers_per_gpu=4,
    train=dict(
        type='RepeatDataset',
        times=15,
        dataset=dict(
            type='ScanNetDataset',
            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='LoadAnnotations3D'),
                dict(type='GlobalAlignment', rotation_axis=2),
                dict(type='PointSample', 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='DefaultFormatBundle3D',
                    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', 'gt_bboxes_3d', 'gt_labels_3d'])
            ],
            filter_empty_gt=False,
            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='ScanNetDataset',
        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='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='DefaultFormatBundle3D',
                        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'])
                ])
        ],
        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='ScanNetDataset',
        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='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='DefaultFormatBundle3D',
                        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'])
                ])
        ],
        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'))
gpu_ids = [0]

2023-12-25 01:48:12,908 - mmdet - INFO - Set random seed to 0, deterministic: False
/opt/conda/lib/python3.7/site-packages/mmcv/runner/base_module.py:127: UserWarning: init_weights of MinkSingleStage3DDetector has been called more than once.
  warnings.warn(f'init_weights of {self.__class__.__name__} has '
2023-12-25 01:48:13,104 - mmdet - INFO - Model:
MinkSingleStage3DDetector(
  (backbone): MinkResNet(
    (conv1): MinkowskiConvolution(in=3, 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)
    (relu): MinkowskiReLU()
    (maxpool): MinkowskiMaxPooling(kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
    (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()
      )
      (2): 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()
      )
      (2): 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()
      )
      (3): 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()
      )
      (2): 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()
      )
      (3): 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()
      )
      (4): 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()
      )
      (5): 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()
      )
      (2): 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()
      )
    )
  )
  (neck): TR3DNeck(
    (lateral_block_0): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
    )
    (out_block_0): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
    )
    (up_block_1): Sequential(
      (0): MinkowskiGenerativeConvolutionTranspose(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()
    )
    (lateral_block_1): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
    )
    (out_block_1): Sequential(
      (0): MinkowskiConvolution(in=128, out=128, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
      (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): MinkowskiReLU()
    )
    (up_block_2): Sequential(
      (0): MinkowskiGenerativeConvolutionTranspose(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()
    )
  )
  (head): TR3DHead(
    (bbox_loss): AxisAlignedIoULoss()
    (cls_loss): FocalLoss()
    (bbox_conv): MinkowskiConvolution(in=128, out=6, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
    (cls_conv): MinkowskiConvolution(in=128, out=18, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
  )
)
2023-12-25 01:48:15,180 - mmdet - INFO - Start running, host: root@efb549353d05, work_dir: /mmdetection3d/work_dirs/tr3d_scannet-3d-18class
2023-12-25 01:48:15,181 - mmdet - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) StepLrUpdaterHook                  
(NORMAL      ) CheckpointHook                     
(LOW         ) EvalHook                           
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) StepLrUpdaterHook                  
(NORMAL      ) EmptyCacheHook                     
(LOW         ) IterTimerHook                      
(LOW         ) EvalHook                           
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_train_iter:
(VERY_HIGH   ) StepLrUpdaterHook                  
(LOW         ) IterTimerHook                      
(LOW         ) EvalHook                           
 -------------------- 
after_train_iter:
(ABOVE_NORMAL) OptimizerHook                      
(NORMAL      ) CheckpointHook                     
(NORMAL      ) EmptyCacheHook                     
(LOW         ) IterTimerHook                      
(LOW         ) EvalHook                           
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) CheckpointHook                     
(NORMAL      ) EmptyCacheHook                     
(LOW         ) EvalHook                           
(VERY_LOW    ) TextLoggerHook                     
 -------------------- 
before_val_epoch:
(NORMAL      ) EmptyCacheHook                     
(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                     
 -------------------- 
2023-12-25 01:48:15,181 - mmdet - INFO - workflow: [('train', 1)], max: 12 epochs
2023-12-25 01:48:15,182 - mmdet - INFO - Checkpoints will be saved to /mmdetection3d/work_dirs/tr3d_scannet-3d-18class by HardDiskBackend.
Traceback (most recent call last):
  File "tools/train.py", line 263, in <module>
    main()
  File "tools/train.py", line 259, in main
    meta=meta)
  File "/mmdetection3d/mmdet3d/apis/train.py", line 351, in train_model
    meta=meta)
  File "/mmdetection3d/mmdet3d/apis/train.py", line 319, in train_detector
    runner.run(data_loaders, cfg.workflow)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 49, in train
    for i, data_batch in enumerate(self.data_loader):
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 681, in __next__
    data = self._next_data()
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1376, in _next_data
    return self._process_data(data)
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1402, in _process_data
    data.reraise()
  File "/opt/conda/lib/python3.7/site-packages/torch/_utils.py", line 461, in reraise
    raise exception
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/opt/conda/lib/python3.7/site-packages/mmdet/datasets/dataset_wrappers.py", line 178, in __getitem__
    return self.dataset[idx % self._ori_len]
  File "/mmdetection3d/mmdet3d/datasets/custom_3d.py", line 435, in __getitem__
    data = self.prepare_train_data(idx)
  File "/mmdetection3d/mmdet3d/datasets/custom_3d.py", line 225, in prepare_train_data
    input_dict = self.get_data_info(index)
  File "/mmdetection3d/mmdet3d/datasets/scannet_dataset.py", line 95, in get_data_info
    info = self.data_infos[index]
KeyError: 1

The data info of ScanNet is generated previous in my local host, which is mapped into the container by

sudo docker run -it --runtime=nvidia -v /home/admin17/vision3d/projects/mmdet3d/mmdetection3d/data/scannet:/mmdetection3d/data/scannet -v /home/admin17/vision3d/projects/tr3d/configs:/mmdetection3d/configs -v /home/admin17/vision3d/projects/tr3d/mmdet3d/datasets:/mmdetection3d/mmdet3d/datasets tr3d:latest

Though the version of mmdetion3d in the docker is 1.0.0rc3 and that in my local host is 1.2.0, I find there is no difference between these two versions for converting ScanNet by comparing the .py files in ./data/scannet. I cannot figure out the reason, could you help me? Any other suggestions that may help to do the test are also welcomed.

filaPro commented 8 months ago

Hi @ChihaoZhang ,

There is probably no difference in data/scannet but there are a lot of differences in tools/dataset_converters. They were introduced in 1.1 release, more info here. I recommend to process the data with our code, or with mmdet3d<1.1.

ChihaoZhang commented 8 months ago

@filaPro, thanks for your quick reply and the problem has been solved now. Apologize for the bother caused by my incomplete checking.