40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
_base_ = [
|
|
'../_base_/datasets/imagenet_bs128_riformer_medium_384.py',
|
|
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
|
|
'../_base_/default_runtime.py',
|
|
]
|
|
|
|
# Model settings
|
|
model = dict(
|
|
type='ImageClassifier',
|
|
backbone=dict(
|
|
type='RIFormer',
|
|
arch='m36',
|
|
drop_path_rate=0.1,
|
|
init_cfg=[
|
|
dict(
|
|
type='TruncNormal',
|
|
layer=['Conv2d', 'Linear'],
|
|
std=.02,
|
|
bias=0.),
|
|
dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
|
|
]),
|
|
neck=dict(type='GlobalAveragePooling'),
|
|
head=dict(
|
|
type='LinearClsHead',
|
|
num_classes=1000,
|
|
in_channels=768,
|
|
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
|
|
))
|
|
|
|
# schedule settings
|
|
optim_wrapper = dict(
|
|
optimizer=dict(lr=4e-3),
|
|
clip_grad=dict(max_norm=5.0),
|
|
)
|
|
|
|
# NOTE: `auto_scale_lr` is for automatically scaling LR
|
|
# based on the actual training batch size.
|
|
# base_batch_size = (32 GPUs) x (128 samples per GPU)
|
|
auto_scale_lr = dict(base_batch_size=4096)
|