43 lines
1.6 KiB
Python
43 lines
1.6 KiB
Python
_base_ = ['./mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py']
|
|
pretrained = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window12_384_22k_20220412-6580f57d.pth' # noqa
|
|
|
|
depths = [2, 2, 18, 2]
|
|
model = dict(
|
|
backbone=dict(
|
|
pretrain_img_size=384,
|
|
embed_dims=192,
|
|
depths=depths,
|
|
num_heads=[6, 12, 24, 48],
|
|
window_size=12,
|
|
init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
|
|
decode_head=dict(in_channels=[192, 384, 768, 1536]))
|
|
|
|
# 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))
|