_base_ = [
    '../_base_/models/vit-base-p16.py',
    '../_base_/datasets/imagenet_bs64_pil_resize.py',
    '../_base_/schedules/imagenet_bs4096_AdamW.py',
    '../_base_/default_runtime.py'
]

# model setting
model = dict(backbone=dict(pre_norm=True))

# data settings
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RandomResizedCrop',
        scale=448,
        backend='pillow',
        interpolation='bicubic'),
    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
    dict(type='PackInputs'),
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='ResizeEdge',
        scale=448,
        edge='short',
        backend='pillow',
        interpolation='bicubic'),
    dict(type='CenterCrop', crop_size=448),
    dict(type='PackInputs'),
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = dict(dataset=dict(pipeline=test_pipeline))

# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))