TypeError: TwoStageDetectionAUGFPN: __init__() got an unexpected keyword argument 'roi_head'

[SaliormoonLadyZhao]

Thanks for your error report and we appreciate it a lot.

Describe the bug

model = dict(
    type='TwoStageDetectorAUGFPN',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        norm_cfg=dict(type='BN', requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='HighFPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[8],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[0.0, 0.0, 0.0, 0.0],
            target_stds=[1.0, 1.0, 1.0, 1.0]),
        loss_cls=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
    bbox_roi_extractor=dict(
        type='StandardRoIHead',
        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
        out_channels=256,
        featmap_strides=[4, 8, 16, 32]),
    bbox_head=dict(
        type='Shared2FCBBoxHead',
        num_fcs=2,
        in_channels=256,
        fc_out_channels=1024,
        roi_feat_size=7,
        num_classes=81,
        target_means=[0.0, 0.0, 0.0, 0.0],
        target_stds=[0.1, 0.1, 0.2, 0.2],
        reg_class_agnostic=False),
    train_cfg=dict(
        rpn=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.3,
                min_pos_iou=0.3,
                ignore_iof_thr=-1),
            sampler=dict(
                type='RandomSampler',
                num=256,
                pos_fraction=0.5,
                neg_pos_ub=-1,
                add_gt_as_proposals=False),
            allowed_border=-1,
            pos_weight=-1,
            debug=False),
        rcnn=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.5,
                neg_iou_thr=0.5,
                min_pos_iou=0.5,
                ignore_iof_thr=-1),
            sampler=dict(
                type='RandomSampler',
                num=512,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True),
            pos_weight=-1,
            use_consistent_supervision=True,
            alpha=0.25,
            debug=False)),
    test_cfg=dict(
        rpn=dict(
            nms_across_levels=False,
            nms_pre=1000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05,
            nms=dict(type='nms', iou_threshold=0.5),
            max_per_img=100,
            use_consistent_supervision=True)),
    roi_head=dict(bbox_head=dict(num_classes=8)))
dataset_type = 'CocoDataset'
data_root = 'datas/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type='CocoDataset',
        ann_file='datas/train.json',
        img_prefix='datas/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
        ],
        classes=('Crack', 'Manhole', 'Net', 'Pothole', 'Patch-Crack',
                 'Patch-Net', 'Patch-Pothole', 'other')),
    val=dict(
        type='CocoDataset',
        ann_file='datas/train.json',
        img_prefix='datas/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        classes=('Crack', 'Manhole', 'Net', 'Pothole', 'Patch-Crack',
                 'Patch-Net', 'Patch-Pothole', 'other')),
    test=dict(
        type='CocoDataset',
        ann_file='datas/train.json',
        img_prefix='datas/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        classes=('Crack', 'Manhole', 'Net', 'Pothole', 'Patch-Crack',
                 'Patch-Net', 'Patch-Pothole', 'other')))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.025, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=100)
checkpoint_config = dict(interval=4)
log_config = dict(interval=10, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
work_dir = './work_dirs/load_aug_50'
gpu_ids = range(0, 1)


**Traceback (most recent call last):
  File "/home/z/miniconda3/lib/python3.7/site-packages/mmcv/utils/registry.py", line 51, in build_from_cfg
    return obj_cls(**args)
TypeError: __init__() got an unexpected keyword argument 'roi_head'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/train.py", line 188, in <module>
    main()
  File "tools/train.py", line 161, in main
    test_cfg=cfg.get('test_cfg'))
  File "/home/z/miniconda3/lib/python3.7/site-packages/mmdet-2.14.0-py3.7.egg/mmdet/models/builder.py", line 58, in build_detector
    cfg, default_args=dict(train_cfg=train_cfg, test_cfg=test_cfg))
  File "/home/z/miniconda3/lib/python3.7/site-packages/mmcv/utils/registry.py", line 210, in build
    return self.build_func(*args, **kwargs, registry=self)
  File "/home/z/miniconda3/lib/python3.7/site-packages/mmcv/cnn/builder.py", line 26, in build_model_from_cfg
    return build_from_cfg(cfg, registry, default_args)
  File "/home/z/miniconda3/lib/python3.7/site-packages/mmcv/utils/registry.py", line 54, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
TypeError: TwoStageDetectorAUGFPN: __init__() got an unexpected keyword argument 'roi_head'**

Reproduction

1. What command or script did you run?

python tools/train.py configs/faster_rcnn/load_aug_50.py --gpus 1

2. Did you make any modifications on the code or config? Did you understand what you have modified?

Using some of the models like 'HighFPN', 'two_stage' in https://github.com/Gus-Guo/AugFPN 'https://github.com/Gus-Guo/AugFPN' is also in MMdetection format

3. What dataset did you use?

A public data set in coco format

Environment

1. Please run python mmdet/utils/collect_env.py to collect necessary environment information and paste it here.

Python: 3.7.0 (default, Oct 9 2018, 10:31:47) [GCC 7.3.0] CUDA available: True GPU 0: NVIDIA GeForce RTX 3090 GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 PyTorch: 1.8.0 TorchVision: 0.9.0 OpenCV: 4.5.5 MMCV: 1.3.9 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 11.1 MMDetection: 2.14.0+

Error traceback If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

[Czm369]

A custom model can completely delete the modified part of the inherited config.

[SaliormoonLadyZhao]

Thank you very much for your reply, but I'm sorry. I'm a new hand, could you please tell me more details? I'm a little confused, thank you

A custom model can completely delete the modified part of the inherited config.

Thank you very much for your reply, but I'm sorry. I'm a new hand, could you please tell me more details? I'm a little confused, thank you

[nomurakeiya]

I'm getting same error.

[FraCamp]

I am having the same problem (different net, vfnet in my case)

[FraCamp]

I am using a custom dataset in order to do so I made a custom config file (adapting the one in the docs) and there is explicitly the rewriting of the model (since there are different classes) where in the model dict there is roi_head as key argument

[FraCamp]

I believe I found the problem, since vfnet has no roi_head keyword I provide only the bbox_head (in order to change the number of classes from 80 (COCO) default to 5 (mine classes)