NUM_CLASSES = 2
CLASSES = ['0', '1']

model = dict(
    type='ImageClassifier',
    backbone=dict(
        type='ConvNeXt',
        arch='base',
        drop_path_rate=0.1,
        layer_scale_init_value=0.0,
        use_grn=True),
    head=dict(
        type='LinearClsHead',
        num_classes=NUM_CLASSES,
        in_channels=1024,
        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.1),
        init_cfg=None),
    init_cfg=dict(
        type='TruncNormal', layer=['Conv2d', 'Linear'], std=0.02, bias=0.0),
    train_cfg=dict(augments=[
        dict(type='Mixup', alpha=0.8),
        dict(type='CutMix', alpha=1.0)
    ]))
dataset_type = 'CustomDataset'
data_preprocessor = dict(
    num_classes=NUM_CLASSES,
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RandomResizedCrop',
        scale=384,
        backend='pillow',
        interpolation='bicubic'),
    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
    dict(type='PackInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', scale=384, backend='pillow', interpolation='bicubic'),
    dict(type='PackInputs')
]
train_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    # batch_size=32,
    batch_size=16,
    num_workers=5,
    dataset=dict(
        type='CustomDataset',
        data_root='../data-raw/external/UTKFace/',
        ann_file='gender_train/gender_train.txt',
        data_prefix='gender_train',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='RandomResizedCrop',
                scale=384,
                backend='pillow',
                interpolation='bicubic'),
            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
            dict(type='PackInputs')
        ],
        with_label=True,
        classes=CLASSES),
    sampler=dict(type='DefaultSampler', shuffle=True))
val_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    # batch_size=64,
    batch_size=16,
    num_workers=5,
    dataset=dict(
        type='CustomDataset',
        data_root='../data-raw/external/UTKFace/',
        ann_file='gender_val/gender_val.txt',
        data_prefix='gender_val',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='Resize',
                scale=384,
                backend='pillow',
                interpolation='bicubic'),
            dict(type='PackInputs')
        ],
        with_label=True,
        classes=CLASSES),
    sampler=dict(type='DefaultSampler', shuffle=False))
val_evaluator = dict(type='Accuracy')
test_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    # batch_size=64,
    batch_size=16,
    num_workers=5,
    dataset=dict(
        type='CustomDataset',
        # data_root='/home/gajjarbhavin99/UTKFace/',
        data_root='../data-raw/external/UTKFace/',
        ann_file='gender_test/gender_test.txt',
        data_prefix='gender_test',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='Resize',
                scale=384,
                backend='pillow',
                interpolation='bicubic'),
            dict(type='PackInputs')
        ],
        with_label=True,
        classes=CLASSES),
    sampler=dict(type='DefaultSampler', shuffle=False))
test_evaluator = dict(type='Accuracy')
optim_wrapper = dict(
    optimizer=dict(
        type='AdamW',
        # lr=0.0025,
        lr=0.0025/32,
        weight_decay=0.05,
        eps=1e-08,
        betas=(0.9, 0.999)),
    paramwise_cfg=dict(
        norm_decay_mult=0.0,
        bias_decay_mult=0.0,
        flat_decay_mult=0.0,
        custom_keys=dict({
            '.absolute_pos_embed': dict(decay_mult=0.0),
            '.relative_position_bias_table': dict(decay_mult=0.0)
        })),
    clip_grad=None)
param_scheduler = [
    dict(
        type='LinearLR',
        start_factor=0.001,
        by_epoch=True,
        end=20,
        convert_to_iter_based=True),
    dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=True, begin=20)
]
train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
val_cfg = dict()
test_cfg = dict()
# auto_scale_lr = dict(base_batch_size=1024)
auto_scale_lr = dict(base_batch_size=32)
default_scope = 'mmpretrain'
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=100),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(type='CheckpointHook', interval=1),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='VisualizationHook', enable=False))
env_cfg = dict(
    cudnn_benchmark=False,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='UniversalVisualizer', vis_backends=[dict(type='LocalVisBackend')])
log_level = 'INFO'
load_from = None
resume = False
randomness = dict(seed=None, deterministic=False)
custom_hooks = [dict(type='EMAHook', momentum=0.0001, priority='ABOVE_NORMAL')]
launcher = 'none'
work_dir = './work_dirs/convnext-v2-base_32xb32_in1k-384px'