（已解决）微小船只目标检测模型不稳定，loss和梯度为nan

        这几天用mmdetection和mmrotate来做微小物体检测的时候，加了一个Rcopypaste的数据增强的trick，发现无论怎么调参，Loss和grad_norm训着训着就变成nan了，换什么loss都不行。

        三天之后理解了。因为船只的尺寸特别小，只有几个像素，所以如果你copypaste的话会丢失很多背景信息，本来船只的识别就很靠背景信息，比如船尾迹之类的，如果你复制粘贴就没有背景信息了，就更难识别了，模型就不稳定了！！！！

        所以解决方式：把Rcopypaste换成RMosaic！就正常了！

        下面贴一下配置文件：

dataset_type = 'DOTADataset'
data_root = '/home/jovyan/mmrotate/data/split_ss_dota/S2/'
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='RRandomFlip',
        flip_ratio=[0.25, 0.25, 0.25],
        direction=['horizontal', 'vertical', 'diagonal'],
        version='le90'),
    dict(
        type='RMosaic', 
        img_scale=(512, 512),
        center_ratio_range=(0.9, 1.1),
        min_bbox_size=0,
        version='le90',
        pad_val=0),
    # dict(
    #     type='RCopyPaste',
    #     max_num_pasted=200,
    #     rbbox_occluded_iou_thr=0.3,
    #     mask_occluded_thr=0,
    #     selected=True,
    #     version='le90',
    # ),
    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'])
]
train_dataset = dict(
    type='MultiImageMixDataset',
    dataset=dict(
        type=dataset_type,
        ann_file=data_root + 'train/annfiles/',
        img_prefix=data_root + 'train/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True)
        ],
        version='le90'
    ),
    pipeline=train_pipeline,
    max_refetch=1000
)
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(512, 512),
        flip=False,
        transforms=[
            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'])
        ])
]
data = dict(
    samples_per_gpu=4,
    workers_per_gpu=4,
    train=train_dataset,
    val=dict(
        type='DOTADataset',
        ann_file=data_root+'val/annfiles/',
        img_prefix=data_root+'val/images/',
        pipeline=test_pipeline,
        version='le90'),
    test=dict(
        type='DOTADataset',
        ann_file=data_root+'test/annfiles/',
        img_prefix=data_root+'test/images/',
        pipeline=test_pipeline,
        version='le90'))
evaluation = dict(interval=1, metric='mAP')

optimizer = dict(type='SGD', lr=0.001, 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=[1, 6, 11])
runner = dict(type='EpochBasedRunner', max_epochs=100)
checkpoint_config = dict(interval=10)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = './work_dirs/my_config/airbus_epoch_20.pth'
resume_from = None
workflow = [('train', 3)]
opencv_num_threads = 0
mp_start_method = 'fork'
angle_version = 'le90'
model = dict(
    type='ReDet',
    backbone=dict(
        type='ReResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        style='pytorch',
        pretrained=None),
    neck=dict(
        type='ReFPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RotatedRPNHead',
        in_channels=256,
        feat_channels=256,
        version='le90',
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[2],
            ratios=[0.5, 1.0, 2.0, 4.0],
            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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
    roi_head=dict(
        type='RoITransRoIHead',
        version='le90',
        num_stages=2,
        stage_loss_weights=[1, 1],
        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]),
            dict(
                type='RotatedSingleRoIExtractor',
                roi_layer=dict(
                    type='RiRoIAlignRotated',
                    out_size=7,
                    num_samples=2,
                    num_orientations=8,
                    clockwise=True),
                out_channels=256,
                featmap_strides=[4, 8, 16, 32])
        ],
        bbox_head=[
            dict(
                type='RotatedShared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=1,
                bbox_coder=dict(
                    type='DeltaXYWHAHBBoxCoder',
                    angle_range='le90',
                    norm_factor=2,
                    edge_swap=True,
                    target_means=[0.0, 0.0, 0.0, 0.0, 0.0],
                    target_stds=[0.1, 0.1, 0.2, 0.2, 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='RotatedShared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=1,
                bbox_coder=dict(
                    type='DeltaXYWHAOBBoxCoder',
                    angle_range='le90',
                    norm_factor=None,
                    edge_swap=True,
                    proj_xy=True,
                    target_means=[0.0, 0.0, 0.0, 0.0, 0.0],
                    target_stds=[0.05, 0.05, 0.1, 0.1, 0.5]),
                reg_class_agnostic=False,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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,
                gpu_assign_thr=200),
            sampler=dict(
                type='RandomSampler',
                num=256,
                pos_fraction=0.5,
                neg_pos_ub=-1,
                add_gt_as_proposals=False),
            allowed_border=0,
            pos_weight=-1,
            debug=False),
        rpn_proposal=dict(
            nms_pre=2000,
            max_per_img=2000,
            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,
                    iou_calculator=dict(type='BboxOverlaps2D')),
                sampler=dict(
                    type='RandomSampler',
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True),
                pos_weight=-1,
                debug=False),
            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,
                    iou_calculator=dict(type='RBboxOverlaps2D')),
                sampler=dict(
                    type='RRandomSampler',
                    num=512,
                    pos_fraction=0.25,
                    neg_pos_ub=-1,
                    add_gt_as_proposals=True),
                pos_weight=-1,
                debug=False)
        ]),
    test_cfg=dict(
        rpn=dict(
            nms_pre=2000,
            max_per_img=2000,
            nms=dict(type='nms', iou_threshold=0.5),
            min_bbox_size=0),
        rcnn=dict(
            nms_pre=2000,
            min_bbox_size=0,
            score_thr=0.05,
            nms=dict(iou_thr=0.1),
            max_per_img=2000)))
classes = ('ship', )
work_dir = './work_dirs/my_config'
auto_resume = False
gpu_ids = range(0, 1)