How to change the Faster rcnn detector to Mask R-CNN ?

[lijoe123]

When i change the faster rcnn to Mask r-cnn, it occur the error AttributeError: 'list' object has no attribute 'shape' after the first epoch train.

Here is my config:

model = dict(
    detector=dict(
        type='MaskRCNN',
        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'),
            plugins=[
                dict(
                    cfg=dict(
                        type='GeneralizedAttention',
                        spatial_range=-1,
                        num_heads=8,
                        attention_type='0010',
                        kv_stride=2),
                    stages=(True, True, False, True),
                    position='after_conv2')
            ],
            dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False),
            stage_with_dcn=(True, True, False, True)),
        neck=dict(
            type='FPN',
            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],
                clip_border=False),
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
        roi_head=dict(
            type='StandardRoIHead',
            bbox_roi_extractor=dict(
                type='SingleRoIExtractor',
                roi_layer=dict(
                    type='RoIAlign', output_size=7, sampling_ratio=0),
                out_channels=256,
                featmap_strides=[4, 8, 16, 32]),
            bbox_head=dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=6,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0.0, 0.0, 0.0, 0.0],
                    target_stds=[0.1, 0.1, 0.2, 0.2],
                    clip_border=False),
                reg_class_agnostic=False,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
            mask_roi_extractor=dict(
                type='SingleRoIExtractor',
                roi_layer=dict(
                    type='RoIAlign', output_size=14, sampling_ratio=0),
                out_channels=256,
                featmap_strides=[4, 8, 16, 32]),
            mask_head=dict(
                type='FCNMaskHead',
                num_convs=4,
                in_channels=256,
                conv_out_channels=256,
                num_classes=6,
                loss_mask=dict(
                    type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
        train_cfg=dict(
            rpn=dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.7,
                    neg_iou_thr=0.3,
                    min_pos_iou=0.3,
                    match_low_quality=True,
                    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),
            rpn_proposal=dict(
                nms_pre=2000,
                max_per_img=1000,
                nms=dict(type='nms', iou_threshold=0.7),
                min_bbox_size=0),
            rcnn=dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.5,
                    neg_iou_thr=0.5,
                    min_pos_iou=0.5,
                    match_low_quality=False,
                    ignore_iof_thr=-1),
                sampler=dict(
                    type='RandomSampler',
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True),
                mask_size=28,
                pos_weight=-1,
                debug=False)),
        test_cfg=dict(
            rpn=dict(
                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,
                mask_thr_binary=0.5)),
        init_cfg=dict(
            type='Pretrained',
            checkpoint='/home/music/Downloads/mmtracking/epoch_24.pth')),
    type='QDTrack',
    track_head=dict(
        type='QuasiDenseTrackHead',
        roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        embed_head=dict(
            type='QuasiDenseEmbedHead',
            num_convs=4,
            num_fcs=1,
            embed_channels=256,
            norm_cfg=dict(type='GN', num_groups=32),
            loss_track=dict(type='MultiPosCrossEntropyLoss', loss_weight=0.25),
            loss_track_aux=dict(
                type='L2Loss',
                neg_pos_ub=3,
                pos_margin=0,
                neg_margin=0.1,
                hard_mining=True,
                loss_weight=1.0)),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0),
        train_cfg=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.5,
                min_pos_iou=0.5,
                match_low_quality=False,
                ignore_iof_thr=-1),
            sampler=dict(
                type='CombinedSampler',
                num=256,
                pos_fraction=0.5,
                neg_pos_ub=3,
                add_gt_as_proposals=True,
                pos_sampler=dict(type='InstanceBalancedPosSampler'),
                neg_sampler=dict(type='RandomSampler')))),
    tracker=dict(
        type='QuasiDenseTracker',
        init_score_thr=0.9,
        obj_score_thr=0.5,
        match_score_thr=0.5,
        memo_tracklet_frames=30,
        memo_backdrop_frames=1,
        memo_momentum=0.8,
        nms_conf_thr=0.5,
        nms_backdrop_iou_thr=0.3,
        nms_class_iou_thr=0.7,
        with_cats=True,
        match_metric='bisoftmax'))
optimizer = dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
lr_config = dict(policy='step', step=[3])
total_epochs = 24
evaluation = dict(metric=['bbox', 'track'], interval=1)
dataset_type = 'CocoVideoDataset'
img_norm_cfg = dict(
    mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
    dict(type='LoadMultiImagesFromFile', to_float32=True),
    dict(type='SeqLoadAnnotations', with_bbox=True, with_mask=True, with_track=True),
    dict(
        type='SeqResize',
        img_scale=(1088, 1088),
        share_params=True,
        ratio_range=(0.8, 1.2),
        keep_ratio=True,
        bbox_clip_border=False),
    dict(type='SeqPhotoMetricDistortion', share_params=True),
    dict(
        type='SeqRandomCrop',
        share_params=False,
        crop_size=(1088, 1088),
        bbox_clip_border=False),
    dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
    dict(
        type='SeqNormalize',
        mean=[103.53, 116.28, 123.675],
        std=[1.0, 1.0, 1.0],
        to_rgb=False),
    dict(type='SeqPad', size_divisor=32),
    dict(type='MatchInstances', skip_nomatch=True),
    dict(
        type='VideoCollect',
        keys=[
            'img', 'gt_bboxes', 'gt_labels', 'gt_masks','gt_match_indices',
            'gt_instance_ids'
        ]),
    dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1088, 1088),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[103.53, 116.28, 123.675],
                std=[1.0, 1.0, 1.0],
                to_rgb=False),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='VideoCollect', keys=['img'])
        ])
]
data_root = '/home/music/Downloads/mmtracking/video_pic/'
data = dict(
    samples_per_gpu=4,
    workers_per_gpu=2,
    train=dict(
        type='CocoVideoDataset',
        classes=('aircraft', 'buildings', 'electrical', 'person', 'tree',
                 'wire'),
        ann_file=
        '/home/music/Downloads/mmtracking/video_pic/annotations/train.json',
        img_prefix='/home/music/Downloads/mmtracking/video_pic/train/',
        ref_img_sampler=dict(
            num_ref_imgs=1,
            frame_range=10,
            filter_key_img=True,
            method='uniform'),
        pipeline=[
            dict(type='LoadMultiImagesFromFile', to_float32=True),
            dict(type='SeqLoadAnnotations', with_bbox=True, with_mask=True, with_track=True),
            dict(
                type='SeqResize',
                img_scale=(1088, 1088),
                share_params=True,
                ratio_range=(0.8, 1.2),
                keep_ratio=True,
                bbox_clip_border=False),
            dict(type='SeqPhotoMetricDistortion', share_params=True),
            dict(
                type='SeqRandomCrop',
                share_params=False,
                crop_size=(1088, 1088),
                bbox_clip_border=False),
            dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
            dict(
                type='SeqNormalize',
                mean=[103.53, 116.28, 123.675],
                std=[1.0, 1.0, 1.0],
                to_rgb=False),
            dict(type='SeqPad', size_divisor=32),
            dict(type='MatchInstances', skip_nomatch=True),
            dict(
                type='VideoCollect',
                keys=[
                    'img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_match_indices',
                    'gt_instance_ids'
                ]),
            dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
        ]),
    val=dict(
        type='CocoVideoDataset',
        classes=('aircraft', 'buildings', 'electrical', 'person', 'tree',
                 'wire'),
        ann_file=
        '/home/music/Downloads/mmtracking/video_pic/annotations/val.json',
        img_prefix='/home/music/Downloads/mmtracking/video_pic/val/',
        ref_img_sampler=None,
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1088, 1088),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[103.53, 116.28, 123.675],
                        std=[1.0, 1.0, 1.0],
                        to_rgb=False),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='VideoCollect', keys=['img'])
                ])
        ]),
    test=dict(
        type='CocoVideoDataset',
        classes=('aircraft', 'buildings', 'electrical', 'person', 'tree',
                 'wire'),
        ann_file=
        '/home/music/Downloads/mmtracking/video_pic/annotations/val.json',
        img_prefix='/home/music/Downloads/mmtracking/video_pic/val/',
        ref_img_sampler=None,
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1088, 1088),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[103.53, 116.28, 123.675],
                        std=[1.0, 1.0, 1.0],
                        to_rgb=False),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='VideoCollect', keys=['img'])
                ])
        ]))
work_dir = 'work_dirs/qdtrack_6class'
gpu_ids = [0]

Could you please give me some advice? Thank you!