code_test/configs/AD_yh/AD_yh_test15_surf.py

_base_ = [
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
    type='ATSS',
    backbone=dict(
        type='ResNeXt',
        depth=101,
        groups=64,
        base_width=4,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        norm_cfg=norm_cfg,
        dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False),
        stage_with_dcn=(False, True, True, True),
        style='pytorch',
        init_cfg=dict(
            type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_output',
        num_outs=5),
    bbox_head=dict(
        type='PAAHead',
        reg_decoded_bbox=True,
        score_voting=True,
        topk=9,
        num_classes=2,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            ratios=[1.0],
            octave_base_scale=8,
            scales_per_octave=1,
            strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[.0, .0, .0, .0],
            target_stds=[0.1, 0.1, 0.2, 0.2]),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='GIoULoss', loss_weight=1.3),
        loss_centerness=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.5)),
    # training and testing settings
    train_cfg=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.1,
            neg_iou_thr=0.1,
            min_pos_iou=0,
            ignore_iof_thr=-1),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.6),
        max_per_img=100))

dataset_type = 'CocoDataset'
classes =  ('zangwuyise', 'guashang')

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='SimpleCopyPaste',
                scale=(0.5, 1.5),
                max_paste_objects=5,
                prob=0.7,
                flip_prob = 0.5,
                occluded_area_thresh=100,
                box_occlusion_thresh=10),
    dict(
        type='Resize',
        img_scale=[(2048, 2048), (2560, 2560)],
        multiscale_mode='range',
        keep_ratio=True),
    dict(type='RandomCrop', crop_size=(2560, 2560), allow_negative_crop=True), 
    dict(type='RandomFlip', flip_ratio=[0.2,0.2,0.2], direction=['horizontal', 'vertical', 'diagonal']),
    dict(type='BrightnessTransform', level=5, prob=0.5),
    dict(type='ContrastTransform', level=5, prob=0.5),
    dict(type='RandomShift', shift_ratio=0.5),
    dict(type='MinIoURandomCrop', min_ious=(0.5, 0.7, 0.9), min_crop_size=0.5),
    dict(type='Normalize', **img_norm_cfg),
    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=[(2560, 2560)],
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]


data = dict(
    samples_per_gpu=1,
    workers_per_gpu=8,
    train=dict(
        type='MultiImageMixDataset',
        dataset=dict(
            type=dataset_type,
            img_prefix='/home/shanwei-luo/teamdata/surf0413/images/',
            classes=classes,
            ann_file='/home/shanwei-luo/teamdata/surf0413/annotations/train_cat_mode.json',
            pipeline=[
                dict(type='LoadImageFromFile'),
                dict(type='LoadAnnotations', with_bbox=True)
            ],
            filter_empty_gt=False,
        ),
        pipeline=train_pipeline),
    
    val=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/teamdata/surf0413/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/teamdata/surf0413/annotations/val_cat_mode.json',
        pipeline=test_pipeline,
        filter_empty_gt=False,),
    test=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/teamdata/surf0413/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/teamdata/surf0413/annotations/val_cat_mode.json',
        pipeline=test_pipeline,
        filter_empty_gt=False))

# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
    policy='CosineAnnealing',
    warmup='linear',
    warmup_iters=2000,
    warmup_ratio=1.0 / 10,
    min_lr_ratio=1e-5)
runner = dict(type='EpochBasedRunner', max_epochs=40)

evaluation = dict(interval=2, metric='bbox')
checkpoint_config = dict(interval=2)

log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])