18 lines
526 B
Python
18 lines
526 B
Python
|
_base_ = [
|
||
|
|
'../_base_/models/riformer/riformer_m36.py',
|
||
|
|
'../_base_/datasets/imagenet_bs128_poolformer_medium_224.py',
|
||
|
|
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
|
||
|
|
'../_base_/default_runtime.py',
|
||
|
|
]
|
||
|
|
|
||
|
|
# 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)
|