norm_cfg = dict(type='BN', requires_grad=True)

model = dict(
    type='EncoderDecoder',
    pretrained=None,
    backbone=dict(
        type='STDCContextPathNet',
        backbone_cfg=dict(
            type='STDCNet',
            stdc_type='STDCNet1',
            in_channels=3,
            channels=(32, 64, 256, 512, 1024),
            bottleneck_type='cat',
            num_convs=4,
            norm_cfg=norm_cfg,
            act_cfg=dict(type='ReLU'),
            with_final_conv=False),
        last_in_channels=(1024, 512),
        out_channels=128,
        ffm_cfg=dict(in_channels=384, out_channels=256, scale_factor=4)),
    decode_head=dict(
        type='FCNHead',
        in_channels=256,
        channels=256,
        num_convs=1,
        num_classes=8,  # ✅ 8 類
        in_index=3,
        concat_input=False,
        dropout_ratio=0.1,
        norm_cfg=norm_cfg,
        align_corners=True,
        sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=[
        dict(
            type='FCNHead',
            in_channels=128,
            channels=64,
            num_convs=1,
            num_classes=8,  # ✅ 8 類
            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=128,
            channels=64,
            num_convs=1,
            num_classes=8,  # ✅ 8 類
            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)),
    ],
    train_cfg=dict(),
    test_cfg=dict(mode='whole')
)

dataset_type = 'Golf8Dataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(mean=[128., 128., 128.], std=[256., 256., 256.], to_rgb=True)
crop_size = (360, 720)

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(type='Resize', img_scale=(724, 362), ratio_range=(0.5, 2.0)),
    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PhotoMetricDistortion'),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(724, 362),
        flip=False,
        transforms=[
            dict(type='Resize', img_scale=(724, 362), keep_ratio=False),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]

data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        data_root=data_root,
        img_dir='leftImg8bit/train',
        ann_dir='gtFine/train',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        data_root=data_root,
        img_dir='leftImg8bit/val',
        ann_dir='gtFine/val',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        data_root=data_root,
        img_dir='leftImg8bit/test',
        ann_dir='gtFine/test',
        pipeline=test_pipeline)
)

log_config = dict(
    interval=50,
    hooks=[dict(type='TextLoggerHook', by_epoch=False)]
)

dist_params = dict(backend='nccl')
log_level = 'INFO'

# ✅ Fine-tune 用設定
load_from = 'C:/Users/rd_de/kneronstdc/work_dirs/meconfig8/0619/latest.pth'
resume_from = None


workflow = [('train', 1)]
cudnn_benchmark = True

# ✅ Fine-tune 推薦學習率
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()

lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=160000)

checkpoint_config = dict(by_epoch=False, interval=16000)
evaluation = dict(interval=16000, metric='mIoU', pre_eval=True)