How should I make config file to train with my customized dataset?

[HitmansGO]

I had already prepared my customized dataset with S3DIS format. And I also referred to mmdection3d's config file https://mmdetection3d.readthedocs.io/en/latest/user_guides/new_data_model.html
but when I run train.py with my own config file, I got this erro:

Traceback (most recent call last):
  File "/home/hfut108/oneformer3d/tools/train.py", line 135, in <module>
    main()
  File "/home/hfut108/oneformer3d/tools/train.py", line 131, in main
    runner.train()
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1777, in train
    model = self.train_loop.run()  # type: ignore
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/mmengine/runner/loops.py", line 96, in run
    self.run_epoch()
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/mmengine/runner/loops.py", line 112, in run_epoch
    for idx, data_batch in enumerate(self.dataloader):
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 681, in __next__
    data = self._next_data()
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1376, in _next_data
    return self._process_data(data)
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1402, in _process_data
    data.reraise()
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/_utils.py", line 461, in reraise
    raise exception
Exception: Caught Exception in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/mmengine/dataset/dataset_wrapper.py", line 171, in __getitem__
    return self.datasets[dataset_idx][sample_idx]
  File "/home/hfut108/anaconda3/envs/openmmlab3d/lib/python3.10/site-packages/mmengine/dataset/base_dataset.py", line 418, in __getitem__
    raise Exception(f'Cannot find valid image after {self.max_refetch}! '
Exception: Cannot find valid image after 1000! Please check your image path and pipeline

and here is my config file:

import sys
sys.path.append("/home/hfut108")

_base_ = [
    'mmdet3d::_base_/default_runtime.py',
]
custom_imports = dict(imports=['oneformer3d.oneformer3d.oneformer3d'])

# model settings
num_channels = 64
num_instance_classes = 2
num_semantic_classes = 2
class_names = ['part','bgpart']
metainfo = dict(classes=class_names)
num_points = 4096

model = dict(
    type='S3DISOneFormer3D',
    data_preprocessor=dict(type='Det3DDataPreprocessor'),
    in_channels=6,
    num_channels=num_channels,
    voxel_size=0.05,
    num_classes=num_instance_classes,
    min_spatial_shape=128,
    backbone=dict(
        type='SpConvUNet',
        num_planes=[num_channels * (i + 1) for i in range(5)],
        return_blocks=True),
    decoder=dict(
        type='QueryDecoder',
        num_layers=3,
        num_classes=num_instance_classes,
        num_instance_queries=400,
        num_semantic_queries=num_semantic_classes,
        num_instance_classes=num_instance_classes,
        in_channels=num_channels,
        d_model=256,
        num_heads=8,
        hidden_dim=1024,
        dropout=0.0,
        activation_fn='gelu',
        iter_pred=True,
        attn_mask=True,
        fix_attention=True,
        objectness_flag=True),
    criterion=dict(
        type='S3DISUnifiedCriterion',
        num_semantic_classes=num_semantic_classes,
        sem_criterion=dict(
            type='S3DISSemanticCriterion',
            loss_weight=5.0),
        inst_criterion=dict(
            type='InstanceCriterion',
            matcher=dict(
                type='HungarianMatcher',
                costs=[
                    dict(type='QueryClassificationCost', weight=0.5),
                    dict(type='MaskBCECost', weight=1.0),
                    dict(type='MaskDiceCost', weight=1.0)]),
            loss_weight=[0.5, 1.0, 1.0, 0.5],
            num_classes=num_instance_classes,
            non_object_weight=0.05,
            fix_dice_loss_weight=True,
            iter_matcher=True,
            fix_mean_loss=True)),
    train_cfg=dict(),
    test_cfg=dict(
        topk_insts=450,
        inst_score_thr=0.0,
        pan_score_thr=0.4,
        npoint_thr=300,
        obj_normalization=True,
        obj_normalization_thr=0.01,
        sp_score_thr=0.15,
        nms=True,
        matrix_nms_kernel='linear',
        num_sem_cls=num_semantic_classes,
        stuff_cls=[1],
        thing_cls=[0]))

# dataset settings
dataset_type = 'S3DISSegDataset_'
data_root = 'data/s3dis/'
data_prefix = dict(
    pts='points',
    pts_instance_mask='instance_mask',
    pts_semantic_mask='semantic_mask')

train_area = [1, 2, 3, 4, 6]
test_area = 5

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',
        with_label_3d=False,
        with_bbox_3d=False,
        with_mask_3d=True,
        with_seg_3d=True),
    dict(
        type='PointSample_',
        num_points=num_points),
    dict(type='PointInstClassMapping_',
        num_classes=num_instance_classes),
    dict(
        type='RandomFlip3D',
        sync_2d=False,
        flip_ratio_bev_horizontal=0.5,
        flip_ratio_bev_vertical=0.5),
    dict(
        type='GlobalRotScaleTrans',
        rot_range=[0.0, 0.0],
        scale_ratio_range=[0.9, 1.1],
        translation_std=[.1, .1, .1],
        shift_height=False),
    dict(
        type='NormalizePointsColor_',
        color_mean=[127.5, 127.5, 127.5]),
    dict(
        type='Pack3DDetInputs_',
        keys=[
            'points', '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='LoadAnnotations3D',
        with_bbox_3d=False,
        with_label_3d=False,
        with_mask_3d=True,
        with_seg_3d=True),
    dict(
        type='MultiScaleFlipAug3D',
        img_scale=(1333, 800),
        pts_scale_ratio=1,
        flip=False,
        transforms=[
            dict(
                type='NormalizePointsColor_',
                color_mean=[127.5, 127.5, 127.5])]),
    dict(type='Pack3DDetInputs_', keys=['points'])
]

# run settings
train_dataloader = dict(
    batch_size=2,
    num_workers=3,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
            type='ConcatDataset',
            datasets=([
                dict(
                    type=dataset_type,
                    data_root=data_root,
                    ann_file=f's3dis_infos_Area_{i}.pkl',
                    pipeline=train_pipeline,
                    metainfo=metainfo,
                    filter_empty_gt=True,
                    data_prefix=data_prefix,
                    box_type_3d='Depth',
                    backend_args=None) for i in train_area])))

val_dataloader = dict(
    batch_size=1,
    num_workers=1,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=f's3dis_infos_Area_{test_area}.pkl',
        pipeline=test_pipeline,
        metainfo=metainfo,
        test_mode=True,
        data_prefix=data_prefix,
        box_type_3d='Depth',
        backend_args=None))
test_dataloader = val_dataloader


label2cat = {i: name for i, name in enumerate(class_names)}
metric_meta = dict(
    label2cat=label2cat,
    ignore_index=[num_semantic_classes],
    classes=class_names,
    dataset_name='S3DIS')
sem_mapping = [0, 1]

val_evaluator = dict(
    type='UnifiedSegMetric',
    stuff_class_inds=[1],
    thing_class_inds=[0],
    min_num_points=1,
    id_offset=2**16,
    sem_mapping=sem_mapping,
    inst_mapping=sem_mapping,
    submission_prefix_semantic=None,
    submission_prefix_instance=None,
    metric_meta=metric_meta)
test_evaluator = val_evaluator

optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='AdamW', lr=0.0001, weight_decay=0.05),
    clip_grad=dict(max_norm=10, norm_type=2))
param_scheduler = dict(type='PolyLR', begin=0, end=512, power=0.9)

custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
default_hooks = dict(
    checkpoint=dict(
        interval=16,
        max_keep_ckpts=1,
        save_best=['all_ap_50%', 'miou'],
        rule='greater'))

load_from = 'work_dirs/tmp/instance-only-oneformer3d_1xb2_scannet-and-structured3d.pth'

train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=512, val_interval=16)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')

I don't know how to fix this erro, so I really need some help.
Expecting for the solution, thx!

[oneformer3d-contributor]

Please debug smth like for b in YourDataset: print b. Because now you have a problem with dataset. It tries to get i-th element 1000 times, all of the attempts fail (probably bug with path to point clouds or to annotation), so you get this error.

[zhaohongxiang-seu]

@HitmansGO I encountered the same issue, have you resolved it?

[ustbwang1jie]

@HitmansGO have you resolved it?

[Lizhinwafu]

[> @HitmansGO have you resolved it?

](#9 (comment))