_base_ = [
    '../_base_/models/bisenetv2.py',
    '../_base_/datasets/cityscapes_1024x1024.py',
    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
]
crop_size = (1024, 1024)
data_preprocessor = dict(size=crop_size)
norm_cfg = dict(type='SyncBN', requires_grad=True)
models = dict(
    data_preprocessor=data_preprocessor,
    decode_head=dict(
        sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000)),
    auxiliary_head=[
        dict(
            type='FCNHead',
            in_channels=16,
            channels=16,
            num_convs=2,
            num_classes=19,
            in_index=1,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=False,
            sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
        dict(
            type='FCNHead',
            in_channels=32,
            channels=64,
            num_convs=2,
            num_classes=19,
            in_index=2,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=False,
            sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
        dict(
            type='FCNHead',
            in_channels=64,
            channels=256,
            num_convs=2,
            num_classes=19,
            in_index=3,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=False,
            sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
        dict(
            type='FCNHead',
            in_channels=128,
            channels=1024,
            num_convs=2,
            num_classes=19,
            in_index=4,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=False,
            sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    ],
)
param_scheduler = [
    dict(type='LinearLR', by_epoch=False, start_factor=0.1, begin=0, end=1000),
    dict(
        type='PolyLR',
        eta_min=1e-4,
        power=0.9,
        begin=1000,
        end=160000,
        by_epoch=False,
    )
]
optimizer = dict(type='SGD', lr=0.05, momentum=0.9, weight_decay=0.0005)
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
train_dataloader = dict(batch_size=4, num_workers=4)
val_dataloader = dict(batch_size=1, num_workers=4)
test_dataloader = val_dataloader