auto_resume = False
checkpoint_config = dict(by_epoch=False, interval=100)
crop_size = (
    512,
    512,
)
cudnn_benchmark = True
data_preprocessor = dict(
    bgr_to_rgb=True,
    mean=[
        123.675,
        116.28,
        103.53,
    ],
    pad_val=0,
    seg_pad_val=255,
    size=(
        512,
        512,
    ),
    std=[
        58.395,
        57.12,
        57.375,
    ],
    type='SegDataPreProcessor')
data_root = 'data/fitc_voc'
dataset_type = 'PascalVOCDataset'
default_hooks = dict(
    checkpoint=dict(by_epoch=False, interval=2000, type='CheckpointHook'),
    logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(type='SegVisualizationHook'))
default_scope = 'mmseg'
dist_params = dict(backend='nccl')
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
gpu_ids = [
    0,
]
img_ratios = [
    0.5,
    0.75,
    1.0,
    1.25,
    1.5,
    1.75,
]
launcher = 'none'
load_from = None
log_config = dict(
    hooks=[
        dict(by_epoch=False, type='TextLoggerHook'),
    ], interval=100)
log_level = 'INFO'
log_processor = dict(by_epoch=False)
lr_config = dict(by_epoch=False, min_lr=0.0001, policy='poly', power=0.9)
model = dict(
    auxiliary_head=dict(
        align_corners=False,
        channels=64,
        concat_input=False,
        dropout_ratio=0.1,
        in_channels=256,
        in_index=2,
        loss_decode=dict(
            loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=False),
        norm_cfg=dict(requires_grad=True, type='SyncBN'),
        num_classes=21,
        num_convs=1,
        type='FCNHead'),
    backbone=dict(
        contract_dilation=True,
        depth=18,
        dilations=(
            1,
            1,
            2,
            4,
        ),
        norm_cfg=dict(requires_grad=True, type='SyncBN'),
        norm_eval=False,
        num_stages=4,
        out_indices=(
            0,
            1,
            2,
            3,
        ),
        strides=(
            1,
            2,
            1,
            1,
        ),
        style='pytorch',
        type='ResNetV1c'),
    data_preprocessor=dict(
        bgr_to_rgb=True,
        mean=[
            123.675,
            116.28,
            103.53,
        ],
        pad_val=0,
        seg_pad_val=255,
        size=(
            512,
            512,
        ),
        std=[
            58.395,
            57.12,
            57.375,
        ],
        type='SegDataPreProcessor'),
    decode_head=dict(
        align_corners=False,
        c1_channels=12,
        c1_in_channels=64,
        channels=128,
        dilations=(
            1,
            12,
            24,
            36,
        ),
        dropout_ratio=0.1,
        in_channels=512,
        in_index=3,
        loss_decode=dict(
            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
        norm_cfg=dict(requires_grad=True, type='SyncBN'),
        num_classes=21,
        type='DepthwiseSeparableASPPHead'),
    pretrained='open-mmlab://resnet18_v1c',
    test_cfg=dict(mode='whole'),
    train_cfg=dict(),
    type='EncoderDecoder')
norm_cfg = dict(requires_grad=True, type='SyncBN')
optim_wrapper = dict(
    clip_grad=None,
    optimizer=dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005),
    type='OptimWrapper')
optimizer = dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005)
param_scheduler = [
    dict(
        begin=0,
        by_epoch=False,
        end=20000,
        eta_min=0.0001,
        power=0.9,
        type='PolyLR'),
]
resume = False
resume_from = None
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='dataset_split/val.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='data/fitc_voc',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                2048,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='PascalVOCDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    interval=500,
    metric=[
        'mIoU',
        'mDice',
        'mFscore',
    ],
    pre_eval=True,
    type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2048,
        2048,
    ), type='Resize'),
    dict(type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
train_cfg = dict(max_iters=80000, type='IterBasedTrainLoop', val_interval=2000)
train_dataloader = dict(
    batch_size=8,
    dataset=dict(
        ann_file='dataset_split/train.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='data/fitc_voc',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations'),
            dict(
                keep_ratio=True,
                ratio_range=(
                    0.5,
                    2.0,
                ),
                scale=(
                    2048,
                    2048,
                ),
                type='RandomResize'),
            dict(
                cat_max_ratio=0.75, crop_size=(
                    512,
                    512,
                ), type='RandomCrop'),
            dict(prob=0.5, type='RandomFlip'),
            dict(type='PhotoMetricDistortion'),
            dict(type='PackSegInputs'),
        ],
        type='PascalVOCDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=True, type='InfiniteSampler'))
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(
        keep_ratio=True,
        ratio_range=(
            0.5,
            2.0,
        ),
        scale=(
            2048,
            2048,
        ),
        type='RandomResize'),
    dict(cat_max_ratio=0.75, crop_size=(
        512,
        512,
    ), type='RandomCrop'),
    dict(prob=0.5, type='RandomFlip'),
    dict(type='PhotoMetricDistortion'),
    dict(type='PackSegInputs'),
]
tta_model = dict(type='SegTTAModel')
tta_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(
        transforms=[
            [
                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
            ],
            [
                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
            ],
            [
                dict(type='LoadAnnotations'),
            ],
            [
                dict(type='PackSegInputs'),
            ],
        ],
        type='TestTimeAug'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='dataset_split/val.txt',
        data_prefix=dict(
            img_path='JPEGImages', seg_map_path='SegmentationClass'),
        data_root='data/fitc_voc',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                2048,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='PascalVOCDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
    interval=500,
    metric=[
        'mIoU',
        'mDice',
        'mFscore',
    ],
    pre_eval=True,
    type='IoUMetric')
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = '/data2/han380/results/mmsegmentation/work_dirs/deeplab_fitc_no_overlap_new_2048_diff_crop_may'
workflow = [
    (
        'train',
        1,
    ),
]