_base_ = [
    '../../_base_/datasets/imagenet_bs64_swin_224.py',
    '../../_base_/default_runtime.py',
]

# model settings
model = dict(
    type='ImageClassifier',
    backbone=dict(
        type='VisionTransformer',
        arch='base',
        img_size=224,
        patch_size=16,
        drop_path_rate=0.1,
        init_cfg=dict(type='Pretrained', checkpoint='', prefix='backbone.')),
    neck=None,
    head=dict(
        type='VisionTransformerClsHead',
        num_classes=1000,
        in_channels=768,
        loss=dict(
            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
        init_cfg=[
            dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
            dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
        ]),
    train_cfg=dict(augments=[
        dict(type='Mixup', alpha=0.8),
        dict(type='CutMix', alpha=1.0)
    ]))

# optimizer
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(
        type='AdamW', lr=5e-4, eps=1e-8, betas=(0.9, 0.999),
        weight_decay=0.05),
    clip_grad=dict(max_norm=5.0),
    paramwise_cfg=dict(
        norm_decay_mult=0.0,
        bias_decay_mult=0.0,
        custom_keys={
            '.cls_token': dict(decay_mult=0.0),
            '.pos_embed': dict(decay_mult=0.0)
        }))

# learning rate scheduler
param_scheduler = [
    dict(
        type='LinearLR',
        start_factor=1e-3,
        begin=0,
        end=5,
        convert_to_iter_based=True),
    dict(
        type='CosineAnnealingLR',
        T_max=145,
        eta_min=1e-5,
        by_epoch=True,
        begin=5,
        end=150,
        convert_to_iter_based=True)
]

# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=150)
val_cfg = dict()
test_cfg = dict()

default_hooks = dict(
    checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))
custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]

randomness = dict(seed=0)