_base_ = [
    './datasets/hsi_detection4x.py', './_base_/default_runtime.py'
]
in_channels = 30
model = dict(
    type='DABDETR',
    num_queries=300,
    with_random_refpoints=False,
    num_patterns=0,
    data_preprocessor=dict(
        type='HSIDetDataPreprocessor',
        pad_size_divisor=1),
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(3, ),
        frozen_stages=-1,
        norm_cfg=dict(type='BN', requires_grad=False),
        in_channels=in_channels,
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='ChannelMapper',
        in_channels=[2048],
        kernel_size=1,
        out_channels=256,
        act_cfg=None,
        norm_cfg=None,
        num_outs=1),
    encoder=dict(
        num_layers=6,
        layer_cfg=dict(
            self_attn_cfg=dict(
                embed_dims=256, num_heads=8, dropout=0., batch_first=True),
            ffn_cfg=dict(
                embed_dims=256,
                feedforward_channels=2048,
                num_fcs=2,
                ffn_drop=0.,
                act_cfg=dict(type='PReLU')))),
    decoder=dict(
        num_layers=6,
        query_dim=4,
        query_scale_type='cond_elewise',
        with_modulated_hw_attn=True,
        layer_cfg=dict(
            self_attn_cfg=dict(
                embed_dims=256,
                num_heads=8,
                attn_drop=0.,
                proj_drop=0.,
                cross_attn=False),
            cross_attn_cfg=dict(
                embed_dims=256,
                num_heads=8,
                attn_drop=0.,
                proj_drop=0.,
                cross_attn=True),
            ffn_cfg=dict(
                embed_dims=256,
                feedforward_channels=2048,
                num_fcs=2,
                ffn_drop=0.,
                act_cfg=dict(type='PReLU'))),
        return_intermediate=True),
    positional_encoding=dict(num_feats=128, temperature=20, normalize=True),
    bbox_head=dict(
        type='DABDETRHead',
        num_classes=16,
        embed_dims=256,
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=5.0),
        loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
    # training and testing settings
    train_cfg=dict(
        assigner=dict(
            type='HungarianAssigner',
            match_costs=[
                dict(type='FocalLossCost', weight=2., eps=1e-8),
                dict(type='BBoxL1Cost', weight=5.0, box_format='xywh'),
                dict(type='IoUCost', iou_mode='giou', weight=2.0)
            ])),
    test_cfg=dict(max_per_img=300))



# optimizer
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='AdamW', lr=0.0001, weight_decay=0.0001),
    clip_grad=dict(max_norm=0.1, norm_type=2),
    paramwise_cfg=dict(
        custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))

# learning policy
max_epochs = 100
train_cfg = dict(
    type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=20)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')

param_scheduler = [
    dict(
        type='MultiStepLR',
        begin=0,
        end=max_epochs,
        by_epoch=True,
        milestones=[90],
        gamma=0.1)
]

# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=4, enable=False)