norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
    type='EncoderDecoder',
    pretrained='pretrain/jx_vit_base_p16_224-80ecf9dd.pth',
    backbone=dict(
        type='VisionTransformer',
        img_size=(512, 512),
        patch_size=16,
        in_channels=3,
        embed_dims=768,
        num_layers=12,
        num_heads=12,
        mlp_ratio=4,
        out_indices=(2, 5, 8, 11),
        qkv_bias=True,
        drop_rate=0.0,
        attn_drop_rate=0.0,
        drop_path_rate=0.0,
        with_cls_token=True,
        norm_cfg=dict(type='LN', eps=1e-06),
        act_cfg=dict(type='GELU'),
        norm_eval=False,
        interpolate_mode='bicubic'),
    neck=dict(
        type='MultiLevelNeck',
        in_channels=[768, 768, 768, 768],
        out_channels=768,
        scales=[4, 2, 1, 0.5]),
    decode_head=dict(
        type='UPerHead',
        in_channels=[768, 768, 768, 768],
        in_index=[0, 1, 2, 3],
        pool_scales=(1, 2, 3, 6),
        channels=512,
        dropout_ratio=0.1,
        num_classes=11,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=dict(
        type='FCNHead',
        in_channels=768,
        in_index=3,
        channels=256,
        num_convs=1,
        concat_input=False,
        dropout_ratio=0.1,
        num_classes=11,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
    train_cfg=dict(),
    test_cfg=dict(mode='whole'))
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=0.0005)
optimizer_config = dict()
lr_config = dict(policy='poly', power=0.9, min_lr=0.0001, by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=20000)
checkpoint_config = dict(by_epoch=False, interval=2000)
evaluation = dict(interval=2000, metric='mIoU', pre_eval=True)
dataset_type = 'TrashDataset'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='CustomLoadAnnotations', coco_json_path='../data/train.json'),
    dict(type='Resize', img_scale=(512, 512), keep_ratio=False),
    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='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(512, 512),
        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=4,
    workers_per_gpu=4,
    train=dict(
        type='TrashDataset',
        coco_json_path='../data/train.json',
        is_valid=False,
        img_dir='../data',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='CustomLoadAnnotations',
                coco_json_path='../data/train.json'),
            dict(type='Resize', img_scale=(512, 512), keep_ratio=False),
            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='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_semantic_seg'])
        ]),
    val=dict(
        type='TrashDataset',
        coco_json_path='../data/val.json',
        is_valid=True,
        img_dir='../data',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(512, 512),
                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='TrashDataset',
        coco_json_path='../data/test.json',
        is_valid=True,
        img_dir='../data',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(512, 512),
                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'])
                ])
        ]))
seed = 0
work_dir = './result/test'
gpu_ids = [0]
auto_resume = False