33 lines
844 B
Python
33 lines
844 B
Python
_base_ = [
|
|
'../_base_/models/dpt_vit-b16.py', '../_base_/datasets/ade20k.py',
|
|
'../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
|
|
]
|
|
|
|
# AdamW optimizer, no weight decay for position embedding & layer norm
|
|
# in backbone
|
|
optimizer = dict(
|
|
_delete_=True,
|
|
type='AdamW',
|
|
lr=0.00006,
|
|
betas=(0.9, 0.999),
|
|
weight_decay=0.01,
|
|
paramwise_cfg=dict(
|
|
custom_keys={
|
|
'pos_embed': dict(decay_mult=0.),
|
|
'cls_token': dict(decay_mult=0.),
|
|
'norm': dict(decay_mult=0.)
|
|
}))
|
|
|
|
lr_config = dict(
|
|
_delete_=True,
|
|
policy='poly',
|
|
warmup='linear',
|
|
warmup_iters=1500,
|
|
warmup_ratio=1e-6,
|
|
power=1.0,
|
|
min_lr=0.0,
|
|
by_epoch=False)
|
|
|
|
# By default, models are trained on 8 GPUs with 2 images per GPU
|
|
data = dict(samples_per_gpu=2, workers_per_gpu=2)
|