_base_ = [
    '../_base_/models/repmlp-base_224.py',
    '../_base_/datasets/imagenet_bs64_pil_resize.py',
    '../_base_/schedules/imagenet_bs4096_AdamW.py',
    '../_base_/default_runtime.py'
]

# model settings
model = dict(backbone=dict(img_size=256))

# dataset settings
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='RandomResizedCrop', scale=256),
    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
    dict(type='PackInputs'),
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='ResizeEdge', scale=292, edge='short', backend='pillow'),
    dict(type='CenterCrop', crop_size=256),
    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 settings
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
# base_batch_size = (8 GPUs) x (64 samples per GPU)
auto_scale_lr = dict(base_batch_size=512)