44 lines
1.3 KiB
Python
44 lines
1.3 KiB
Python
_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(img_size=384))
|
|
|
|
# dataset setting
|
|
preprocess_cfg = dict(
|
|
mean=[127.5, 127.5, 127.5],
|
|
std=[127.5, 127.5, 127.5],
|
|
# convert image from BGR to RGB
|
|
to_rgb=True,
|
|
)
|
|
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='RandomResizedCrop', scale=384, backend='pillow'),
|
|
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
|
|
dict(type='PackClsInputs'),
|
|
]
|
|
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
|
|
dict(type='CenterCrop', crop_size=384),
|
|
dict(type='PackClsInputs'),
|
|
]
|
|
|
|
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))
|
|
|
|
# NOTE: `auto_scale_lr` is for automatically scaling LR,
|
|
# USER SHOULD NOT CHANGE ITS VALUES.
|
|
# base_batch_size = (64 GPUs) x (64 samples per GPU)
|
|
auto_scale_lr = dict(base_batch_size=4096)
|