44 lines
1.1 KiB
Python
44 lines
1.1 KiB
Python
_base_ = [
|
|
'../../_base_/datasets/imagenet_bs64_swin_224.py',
|
|
'../../_base_/schedules/imagenet_bs1024_adamw_swin.py',
|
|
'../../_base_/default_runtime.py'
|
|
]
|
|
|
|
data_preprocessor = dict(
|
|
num_classes=1000,
|
|
# RGB format normalization parameters
|
|
mean=[127.5, 127.5, 127.5],
|
|
std=[127.5, 127.5, 127.5],
|
|
# convert image from BGR to RGB
|
|
to_rgb=True,
|
|
)
|
|
|
|
model = dict(
|
|
type='ImageClassifier',
|
|
backbone=dict(
|
|
type='BEiTViT',
|
|
arch='base',
|
|
img_size=224,
|
|
patch_size=16,
|
|
out_type='avg_featmap',
|
|
use_abs_pos_emb=False,
|
|
use_rel_pos_bias=True,
|
|
use_shared_rel_pos_bias=False,
|
|
),
|
|
neck=None,
|
|
head=dict(
|
|
type='LinearClsHead',
|
|
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=.02),
|
|
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)
|
|
]))
|