_base_ = [
    'mmdet::_base_/models/mask-rcnn_r50_fpn.py',
    'mmdet::_base_/datasets/coco_instance.py',
    'mmdet::_base_/schedules/schedule_1x.py',
    'mmdet::_base_/default_runtime.py'
]

# please install the mmclassification dev-1.x branch
# import mmcls.models to trigger register_module in mmcls
custom_imports = dict(imports=['mmcls.models'], allow_failed_imports=False)
checkpoint_file = 'https://download.openmmlab.com/mmclassification/v0/convnext-v2/convnext-v2-base_3rdparty-fcmae_in1k_20230104-8a798eaf.pth'  # noqa
image_size = (1024, 1024)

model = dict(
    backbone=dict(
        _delete_=True,
        type='mmcls.ConvNeXt',
        arch='base',
        out_indices=[0, 1, 2, 3],
        # TODO: verify stochastic depth rate {0.1, 0.2, 0.3, 0.4}
        drop_path_rate=0.4,
        layer_scale_init_value=0.,  # disable layer scale when using GRN
        gap_before_final_norm=False,
        use_grn=True,  # V2 uses GRN
        init_cfg=dict(
            type='Pretrained', checkpoint=checkpoint_file,
            prefix='backbone.')),
    neck=dict(in_channels=[128, 256, 512, 1024]),
    test_cfg=dict(
        rpn=dict(nms=dict(type='nms')),  # TODO: does RPN use soft_nms?
        rcnn=dict(nms=dict(type='soft_nms'))))

train_pipeline = [
    dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(
        type='RandomResize',
        scale=image_size,
        ratio_range=(0.1, 2.0),
        keep_ratio=True),
    dict(
        type='RandomCrop',
        crop_type='absolute_range',
        crop_size=image_size,
        recompute_bbox=True,
        allow_negative_crop=True),
    dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]

train_dataloader = dict(
    batch_size=4,  # total_batch_size 32 = 8 GPUS x 4 images
    num_workers=8,
    dataset=dict(pipeline=train_pipeline))

max_epochs = 36
train_cfg = dict(max_epochs=max_epochs)

# learning rate
param_scheduler = [
    dict(
        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0,
        end=1000),
    dict(
        type='MultiStepLR',
        begin=0,
        end=max_epochs,
        by_epoch=True,
        milestones=[27, 33],
        gamma=0.1)
]

# Enable automatic-mixed-precision training with AmpOptimWrapper.
optim_wrapper = dict(
    type='AmpOptimWrapper',
    constructor='LearningRateDecayOptimizerConstructor',
    paramwise_cfg={
        'decay_rate': 0.95,
        'decay_type': 'layer_wise',  # TODO: sweep layer-wise lr decay?
        'num_layers': 12
    },
    optimizer=dict(
        _delete_=True,
        type='AdamW',
        lr=0.0001,
        betas=(0.9, 0.999),
        weight_decay=0.05,
    ))

default_hooks = dict(checkpoint=dict(max_keep_ckpts=1))