norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
    type='EncoderDecoder',
    backbone=dict(
        type='VisionTransformer',
        model_name='vit_base_patch16_224',
        img_size=768,
        patch_size=16,
        in_chans=3,
        embed_dim=768,
        depth=12,
        num_heads=12,
        num_classes=104,
        drop_rate=0.0,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        pos_embed_interp=True,
        align_corners=False),
    decode_head=dict(
        type='VisionTransformerUpHead',
        in_channels=768,
        channels=512,
        in_index=11,
        img_size=768,
        embed_dim=768,
        num_classes=104,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        num_conv=2,
        upsampling_method='bilinear',
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=[
        dict(
            type='VisionTransformerUpHead',
            in_channels=768,
            channels=512,
            in_index=5,
            img_size=768,
            embed_dim=768,
            num_classes=104,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
        dict(
            type='VisionTransformerUpHead',
            in_channels=768,
            channels=512,
            in_index=7,
            img_size=768,
            embed_dim=768,
            num_classes=104,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
        dict(
            type='VisionTransformerUpHead',
            in_channels=768,
            channels=512,
            in_index=9,
            img_size=768,
            embed_dim=768,
            num_classes=104,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4))
    ])
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(768, 768), stride=(512, 512))
dataset_type = 'CustomDataset'
data_root = './data/FoodSeg103/Images/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (768, 768)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
    dict(type='RandomCrop', crop_size=(768, 768), cat_max_ratio=0.75),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PhotoMetricDistortion'),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size=(768, 768), 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=(2049, 1025),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=1,
    workers_per_gpu=2,
    train=dict(
        type='CustomDataset',
        data_root='./data/FoodSeg103/Images/',
        img_dir='img_dir/train',
        ann_dir='ann_dir/train',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations'),
            dict(
                type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
            dict(type='RandomCrop', crop_size=(768, 768), cat_max_ratio=0.75),
            dict(type='RandomFlip', prob=0.5),
            dict(type='PhotoMetricDistortion'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size=(768, 768), pad_val=0, seg_pad_val=255),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_semantic_seg'])
        ]),
    val=dict(
        type='CustomDataset',
        data_root='./data/FoodSeg103/Images/',
        img_dir='img_dir/test',
        ann_dir='ann_dir/test',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(2049, 1025),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='CustomDataset',
        data_root='./data/FoodSeg103/Images/',
        img_dir='img_dir/test',
        ann_dir='ann_dir/test',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(2049, 1025),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
log_config = dict(
    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True
optimizer = dict(
    type='SGD',
    lr=0.01,
    momentum=0.9,
    weight_decay=0.0,
    paramwise_cfg=dict(custom_keys=dict(head=dict(lr_mult=10.0))))
optimizer_config = dict()
lr_config = dict(policy='poly', power=0.9, min_lr=0.0001, by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=80000)
checkpoint_config = dict(by_epoch=False, interval=4000)
evaluation = dict(interval=4000, metric='mIoU')
find_unused_parameters = True
work_dir = 'checkpoints/SETR_NAIVE'
gpu_ids = range(0, 1)