search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.23k stars 9.4k forks source link

Error occurs when training own dataset #10671

Open yeungkong opened 1 year ago

yeungkong commented 1 year ago

Hi developer. I am encountering an error when training my own dataset. The following is my config.py.

_base_ = [
    'configs/_base_/models/mask-rcnn_r50_fpn.py',
    'configs/_base_/datasets/coco_instance.py', 'configs/_base_/default_runtime.py'
]

classes = ('liuman','BG')

model = dict(
    # set None to avoid loading ImageNet pre-trained backbone,
    # instead here we set `load_from` to load from COCO pre-trained detectors.
    backbone=dict(init_cfg=None),
    # replace neck from defaultly `FPN` to our new implemented module `AugFPN`
    neck=dict(
        type='HRFPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    # We also need to change the num_classes in head from 80 to 8, to match the
    # cityscapes dataset's annotation. This modification involves `bbox_head` and `mask_head`.
    roi_head=dict(
        bbox_head=[
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                # change the number of classes from defaultly COCO to cityscapes
                num_classes=2,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.1, 0.1, 0.2, 0.2]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                # change the number of classes from defaultly COCO to cityscapes
                num_classes=2,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.05, 0.05, 0.1, 0.1]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                # change the number of classes from defaultly COCO to cityscapes
                num_classes=2,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.033, 0.033, 0.067, 0.067]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
        ],
        mask_head=dict(
            type='FCNMaskHead',
            num_convs=4,
            in_channels=256,
            conv_out_channels=256,
            # change the number of classes from default COCO to cityscapes
            num_classes=2,
            loss_mask=dict(
                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))))

# over-write `train_pipeline` for new added `AutoAugment` training setting
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(
        type='AutoAugment',
        policies=[
            [dict(
                 type='Rotate',
                 level=5,
                 img_border_value=(124, 116, 104),
                 prob=0.5)
            ],
            [dict(type='Rotate', level=7, img_border_value=(124, 116, 104)),
             dict(
                 type='TranslateX',
                 level=5,
                 prob=0.5,
                 img_border_value=(124, 116, 104))
            ],
        ]),
    dict(
        type='RandomResize',
        scale=[(2048, 800), (2048, 1024)],
        keep_ratio=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs'),
]

# set batch_size per gpu, and set new training pipeline
train_dataloader = dict(
    batch_size=1,
    num_workers=3,
    # over-write `pipeline` with new training pipeline setting
    dataset=dict(pipeline=train_pipeline))

# Set optimizer
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001))

# Set customized learning policy
param_scheduler = [
    dict(
        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
    dict(
        type='MultiStepLR',
        begin=0,
        end=10,
        by_epoch=True,
        milestones=[8],
        gamma=0.1)
]

# train, val, test loop config
train_cfg = dict(max_iters=10, val_interval=1)

The following is the error message.

loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Traceback (most recent call last):
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\registry\build_functions.py", line 122, in build_from_cfg
    obj = obj_cls(**args)  # type: ignore
  File "d:\np\mmdetection\mmdet\datasets\base_det_dataset.py", line 44, in __init__
    super().__init__(*args, **kwargs)
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\dataset\base_dataset.py", line 245, in __init__
    self.full_init()
  File "d:\np\mmdetection\mmdet\datasets\base_det_dataset.py", line 82, in full_init
    self.data_bytes, self.data_address = self._serialize_data()
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\dataset\base_dataset.py", line 766, in _serialize_data
    data_bytes = np.concatenate(data_list)
  File "<__array_function__ internals>", line 180, in concatenate
ValueError: need at least one array to concatenate

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/train.py", line 133, in <module>
    main()
  File "tools/train.py", line 129, in main
    runner.train()
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\runner\runner.py", line 1701, in train
    self._train_loop = self.build_train_loop(
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\runner\runner.py", line 1503, in build_train_loop
    loop = IterBasedTrainLoop(
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\runner\loops.py", line 219, in __init__
    super().__init__(runner, dataloader)
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\runner\base_loop.py", line 26, in __init__
    self.dataloader = runner.build_dataloader(
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\runner\runner.py", line 1351, in build_dataloader
    dataset = DATASETS.build(dataset_cfg)
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\registry\registry.py", line 570, in build
    return self.build_func(cfg, *args, **kwargs, registry=self)
  File "D:\Programs\Anaconda3\envs\NP\lib\site-packages\mmengine\registry\build_functions.py", line 144, in build_from_cfg
    raise type(e)(
ValueError: class `CocoDataset` in mmdet/datasets/coco.py: need at least one array to concatenate

Did I set the config correctly? Please kindly help me. Thank you very much.

shallweiwei commented 1 year ago

You'd better share your dataset config