53 lines
1.8 KiB
Python
53 lines
1.8 KiB
Python
_base_ = ['./mask2former_r50_8xb2-90k_cityscapes-512x1024.py']
|
|
pretrained = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_tiny_patch4_window7_224_20220317-1cdeb081.pth' # noqa
|
|
depths = [2, 2, 6, 2]
|
|
model = dict(
|
|
backbone=dict(
|
|
_delete_=True,
|
|
type='SwinTransformer',
|
|
embed_dims=96,
|
|
depths=depths,
|
|
num_heads=[3, 6, 12, 24],
|
|
window_size=7,
|
|
mlp_ratio=4,
|
|
qkv_bias=True,
|
|
qk_scale=None,
|
|
drop_rate=0.,
|
|
attn_drop_rate=0.,
|
|
drop_path_rate=0.3,
|
|
patch_norm=True,
|
|
out_indices=(0, 1, 2, 3),
|
|
with_cp=False,
|
|
frozen_stages=-1,
|
|
init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
|
|
decode_head=dict(in_channels=[96, 192, 384, 768]))
|
|
|
|
# set all layers in backbone to lr_mult=0.1
|
|
# set all norm layers, position_embeding,
|
|
# query_embeding, level_embeding to decay_multi=0.0
|
|
backbone_norm_multi = dict(lr_mult=0.1, decay_mult=0.0)
|
|
backbone_embed_multi = dict(lr_mult=0.1, decay_mult=0.0)
|
|
embed_multi = dict(lr_mult=1.0, decay_mult=0.0)
|
|
custom_keys = {
|
|
'backbone': dict(lr_mult=0.1, decay_mult=1.0),
|
|
'backbone.patch_embed.norm': backbone_norm_multi,
|
|
'backbone.norm': backbone_norm_multi,
|
|
'absolute_pos_embed': backbone_embed_multi,
|
|
'relative_position_bias_table': backbone_embed_multi,
|
|
'query_embed': embed_multi,
|
|
'query_feat': embed_multi,
|
|
'level_embed': embed_multi
|
|
}
|
|
custom_keys.update({
|
|
f'backbone.stages.{stage_id}.blocks.{block_id}.norm': backbone_norm_multi
|
|
for stage_id, num_blocks in enumerate(depths)
|
|
for block_id in range(num_blocks)
|
|
})
|
|
custom_keys.update({
|
|
f'backbone.stages.{stage_id}.downsample.norm': backbone_norm_multi
|
|
for stage_id in range(len(depths) - 1)
|
|
})
|
|
# optimizer
|
|
optim_wrapper = dict(
|
|
paramwise_cfg=dict(custom_keys=custom_keys, norm_decay_mult=0.0))
|