-
Notifications
You must be signed in to change notification settings - Fork 2.5k
/
knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k.py
55 lines (53 loc) · 1.98 KB
/
knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
_base_ = 'knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k.py'
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window7_224_22k_20220308-d5bdebaf.pth' # noqa
# model settings
model = dict(
pretrained=checkpoint_file,
backbone=dict(
embed_dims=192,
depths=[2, 2, 18, 2],
num_heads=[6, 12, 24, 48],
window_size=7,
use_abs_pos_embed=False,
drop_path_rate=0.4,
patch_norm=True),
decode_head=dict(
kernel_generate_head=dict(in_channels=[192, 384, 768, 1536])),
auxiliary_head=dict(in_channels=768))
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (640, 640)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=True),
dict(type='Resize', img_scale=(2048, 640), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 640),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# In K-Net implementation we use batch size 2 per GPU as default
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))