_base_ = './rtmdet-ins_l_8xb32-300e_coco.py'
checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth'  # noqa
model = dict(
    backbone=dict(
        deepen_factor=0.33,
        widen_factor=0.5,
        init_cfg=dict(
            type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
    neck=dict(in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1),
    bbox_head=dict(in_channels=128, feat_channels=128))

train_pipeline = [
    dict(
        type='LoadImageFromFile',
        file_client_args={{_base_.file_client_args}}),
    dict(
        type='LoadAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(type='CachedMosaic', img_scale=(640, 640), pad_val=114.0),
    dict(
        type='RandomResize',
        scale=(1280, 1280),
        ratio_range=(0.5, 2.0),
        keep_ratio=True),
    dict(
        type='RandomCrop',
        crop_size=(640, 640),
        recompute_bbox=True,
        allow_negative_crop=True),
    dict(type='YOLOXHSVRandomAug'),
    dict(type='RandomFlip', prob=0.5),
    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
    dict(
        type='CachedMixUp',
        img_scale=(640, 640),
        ratio_range=(1.0, 1.0),
        max_cached_images=20,
        pad_val=(114, 114, 114)),
    dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1)),
    dict(type='PackDetInputs')
]

train_pipeline_stage2 = [
    dict(
        type='LoadImageFromFile',
        file_client_args={{_base_.file_client_args}}),
    dict(
        type='LoadAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(
        type='RandomResize',
        scale=(640, 640),
        ratio_range=(0.5, 2.0),
        keep_ratio=True),
    dict(
        type='RandomCrop',
        crop_size=(640, 640),
        recompute_bbox=True,
        allow_negative_crop=True),
    dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1)),
    dict(type='YOLOXHSVRandomAug'),
    dict(type='RandomFlip', prob=0.5),
    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
    dict(type='PackDetInputs')
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))

custom_hooks = [
    dict(
        type='EMAHook',
        ema_type='ExpMomentumEMA',
        momentum=0.0002,
        update_buffers=True,
        priority=49),
    dict(
        type='PipelineSwitchHook',
        switch_epoch=280,
        switch_pipeline=train_pipeline_stage2)
]