_base_ = '../cascade_rcnn/cascade-mask-rcnn_r50_fpn_1x_coco.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)

model = dict(
    # use ResNeSt img_norm
    data_preprocessor=dict(
        mean=[123.68, 116.779, 103.939],
        std=[58.393, 57.12, 57.375],
        bgr_to_rgb=True),
    backbone=dict(
        type='ResNeSt',
        stem_channels=64,
        depth=50,
        radix=2,
        reduction_factor=4,
        avg_down_stride=True,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        norm_cfg=norm_cfg,
        norm_eval=False,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='open-mmlab://resnest50')),
    roi_head=dict(
        bbox_head=[
            dict(
                type='Shared4Conv1FCBBoxHead',
                in_channels=256,
                conv_out_channels=256,
                fc_out_channels=1024,
                norm_cfg=norm_cfg,
                roi_feat_size=7,
                num_classes=80,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.1, 0.1, 0.2, 0.2]),
                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='Shared4Conv1FCBBoxHead',
                in_channels=256,
                conv_out_channels=256,
                fc_out_channels=1024,
                norm_cfg=norm_cfg,
                roi_feat_size=7,
                num_classes=80,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.05, 0.05, 0.1, 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='Shared4Conv1FCBBoxHead',
                in_channels=256,
                conv_out_channels=256,
                fc_out_channels=1024,
                norm_cfg=norm_cfg,
                roi_feat_size=7,
                num_classes=80,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.033, 0.033, 0.067, 0.067]),
                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))
        ],
        mask_head=dict(norm_cfg=norm_cfg)))

train_pipeline = [
    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
    dict(
        type='LoadAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(
        type='RandomChoiceResize',
        scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
                (1333, 768), (1333, 800)],
        keep_ratio=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]

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