search

SJTU-Thinklab-Det / r3det-pytorch

R3Det based on mmdet 2.19.0
Apache License 2.0
42 stars 7 forks source link

用HRSC2016进行训练时，报错KeyError: 'ship' #12

Closed LastSummer09 closed 2 years ago

LastSummer09 commented 2 years ago

我仿照DOTA的配置文件写了一个MyDataset类，并只把 CLASSES = ('plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle', 'large-vehicle', 'ship', 'tennis-court', 'basketball-court', 'storage-tank', 'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter') 改为了： CLASSES = 'ship' 以下为运行后自动生成的代码

data_root = '/content/drive/MyDrive/HRSC2016/'
img_norm_cfg = dict(
    mean=[70.954, 81.526, 78.456], std=[58.371, 57.745, 50.858], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='RResize', img_scale=(512, 512)),
    dict(type='RRandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[70.954, 81.526, 78.456],
        std=[58.371, 57.745, 50.858],
        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=(512, 512),
        flip=False,
        transforms=[
            dict(type='RResize'),
            dict(
                type='Normalize',
                mean=[70.954, 81.526, 78.456],
                std=[58.371, 57.745, 50.858],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type='MyDataset',
        ann_file='/content/drive/MyDrive/HRSC2016/Train/labelTxt/',
        img_prefix='/content/drive/MyDrive/HRSC2016/Train/AllImages/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(type='RResize', img_scale=(512, 512)),
            dict(type='RRandomFlip', flip_ratio=0.5),
            dict(
                type='Normalize',
                mean=[70.954, 81.526, 78.456],
                std=[58.371, 57.745, 50.858],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
        ]),
    val=dict(
        type='MyDataset',
        ann_file='/content/drive/MyDrive/HRSC2016/Test/labelTxt/',
        img_prefix='/content/drive/MyDrive/HRSC2016/Test/AllImages/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(512, 512),
                flip=False,
                transforms=[
                    dict(type='RResize'),
                    dict(
                        type='Normalize',
                        mean=[70.954, 81.526, 78.456],
                        std=[58.371, 57.745, 50.858],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='DefaultFormatBundle'),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='MyDataset',
        ann_file='/content/drive/MyDrive/HRSC2016/Test/Annotations/',
        img_prefix='/content/drive/MyDrive/HRSC2016/Test/AllImages/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(512, 512),
                flip=False,
                transforms=[
                    dict(type='RResize'),
                    dict(
                        type='Normalize',
                        mean=[70.954, 81.526, 78.456],
                        std=[58.371, 57.745, 50.858],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='DefaultFormatBundle'),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
evaluation = dict(interval=12, metric='mAP')
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))
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.3333333333333333,
    step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
checkpoint_config = dict(interval=12)
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)]
model = dict(
    type='R3Det',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        zero_init_residual=False,
        norm_cfg=dict(type='BN', requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5),
    bbox_head=dict(
        type='RRetinaHead',
        num_classes=15,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        anchor_generator=dict(
            type='RAnchorGenerator',
            octave_base_scale=4,
            scales_per_octave=3,
            ratios=[1.0, 0.5, 2.0],
            strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type='DeltaXYWHAOBBoxCoder',
            target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
            target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
    frm_cfgs=[dict(in_channels=256, featmap_strides=[8, 16, 32, 64, 128])],
    num_refine_stages=1,
    refine_heads=[
        dict(
            type='RRetinaRefineHead',
            num_classes=15,
            in_channels=256,
            stacked_convs=4,
            feat_channels=256,
            assign_by_circumhbbox=None,
            anchor_generator=dict(
                type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
            bbox_coder=dict(
                type='DeltaXYWHAOBBoxCoder',
                target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
                target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
            loss_cls=dict(
                type='FocalLoss',
                use_sigmoid=True,
                gamma=2.0,
                alpha=0.25,
                loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0))
    ],
    train_cfg=dict(
        s0=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.5,
                neg_iou_thr=0.4,
                min_pos_iou=0,
                ignore_iof_thr=-1,
                iou_calculator=dict(type='RBboxOverlaps2D_v1')),
            allowed_border=-1,
            pos_weight=-1,
            debug=False),
        sr=[
            dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.6,
                    neg_iou_thr=0.5,
                    min_pos_iou=0,
                    ignore_iof_thr=-1,
                    iou_calculator=dict(type='RBboxOverlaps2D_v1')),
                allowed_border=-1,
                pos_weight=-1,
                debug=False)
        ],
        stage_loss_weights=[1.0]),
    test_cfg=dict(
        nms_pre=2000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(iou_thr=0.1),
        max_per_img=2000))
work_dir = './work_dirs/r3det_r50_fpn_1x_dota_v1'
gpu_ids = range(0, 1)```

以下为报错：

2022-03-19 09:44:59,167 - mmdet - INFO - initialize ResNet with init_cfg {'type': 'Pretrained', 'checkpoint': 'torchvision://resnet50'} 2022-03-19 09:44:59,168 - mmcv - INFO - load model from: torchvision://resnet50 2022-03-19 09:44:59,168 - mmcv - INFO - load checkpoint from torchvision path: torchvision://resnet50 2022-03-19 09:44:59,410 - mmcv - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

2022-03-19 09:44:59,444 - mmdet - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 52, in build_from_cfg return obj_cls(args) File "/content/drive/MyDrive/Colab/r3det-pytorch-main/r3det/datasets/mydataset1.py", line 47, in init super(MyDataset, self).init(ann_file, pipeline, kwargs) File "/usr/local/lib/python3.7/dist-packages/mmdet/datasets/custom.py", line 95, in init self.data_infos = self.load_annotations(local_path) File "/content/drive/MyDrive/Colab/r3det-pytorch-main/r3det/datasets/mydataset1.py", line 102, in load_annotations label = cls_map[cls_name] KeyError: 'ship'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "./tools/train.py", line 193, in main() File "./tools/train.py", line 169, in main datasets = [build_dataset(cfg.data.train)] File "/usr/local/lib/python3.7/dist-packages/mmdet/datasets/builder.py", line 81, in build_dataset dataset = build_from_cfg(cfg, DATASETS, default_args) File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 55, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') KeyError: "MyDataset: 'ship'"



目前推测是单类训练导致的问题，因为CSDN上也有人反映：
![image](https://user-images.githubusercontent.com/76859231/159116704-7d0f6225-f09b-4734-a816-1e4c79f85204.png)
想知道大佬有没有解决这个问题的思路呢？
yangxue0827 commented 2 years ago

Duplicate with https://github.com/open-mmlab/mmrotate/issues/149