Skip to content

Commit 01a38c9

Browse files
ebhrzebhrz
committed
add config support
1 parent ee37cf0 commit 01a38c9

File tree

893 files changed

+29438
-73
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

893 files changed

+29438
-73
lines changed

‎README.md

+166-67
Large diffs are not rendered by default.

‎config/ade20k.json

+31
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,31 @@
1+
{
2+
"bag_file":"/home/hrz/project/fdata/indoor/2022-12-05-17-14-13.bag",
3+
"pose_file":"/home/hrz/project/fdata/indoor/result/pose6d.csv",
4+
"start_time":0,
5+
"play_time":-1,
6+
"LiDAR_topic":"/velodyne_points",
7+
"camera_topic":"/zed2/zed_node/left/image_rect_color/compressed",
8+
"image_compressed":true,
9+
"extrinsic":
10+
[
11+
[ 1.0102, -0.0026, -0.0087, 0.1135],
12+
[-0.0033, -0.0030, -0.9963, -0.1617],
13+
[ 0.0049, 0.9962, -0.0287, 0.0516],
14+
[ 0.0000, 0.0000, 0.0000, 1.0000]
15+
],
16+
"intrinsic":
17+
[
18+
[543.5046, 0, 630.7183],
19+
[0, 540.5383, 350.9063],
20+
[0, 0, 1]
21+
],
22+
"distortion_matrix":[-1.05873889e-01, 1.32265629e-01, -8.55667814e-05,-1.04098281e-03, -7.01241428e-02],
23+
"save_folder":"result/indoor",
24+
"mode":"indoor",
25+
"model_config":"imseg/mmseg/configs/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k.py",
26+
"model_file":"imseg/mmseg/model/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k_20220318_091743-9ba68901.pth",
27+
"lane_class":24,
28+
"pole_class":45,
29+
"predict_func":"get_predict_func_mmlab",
30+
"cmap":"ade20k"
31+
}

‎config/indoor_config.json

+1-1
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,6 @@
2626
"model_file":"imseg/mask2former/model/model.pkl",
2727
"lane_class":24,
2828
"pole_class":45,
29-
"predict_func":"get_predict_func",
29+
"predict_func":"get_predict_func_detectron",
3030
"cmap":"mapillary"
3131
}

‎config/outdoor_config.json

+1-1
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,6 @@
2727
"model_file":"imseg/mask2former/model/model.pkl",
2828
"lane_class":24,
2929
"pole_class":45,
30-
"predict_func":"get_predict_func",
30+
"predict_func":"get_predict_func_detectron",
3131
"cmap":"mapillary"
3232
}

‎config/outdoor_distortion_config.json

+1-1
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,6 @@
2727
"model_file":"imseg/mask2former/model/model.pkl",
2828
"lane_class":24,
2929
"pole_class":45,
30-
"predict_func":"get_predict_func",
30+
"predict_func":"get_predict_func_detectron",
3131
"cmap":"mapillary"
3232
}

‎imseg/mmseg/_base_/datasets/ade20k.py

+54
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
# dataset settings
2+
dataset_type = 'ADE20KDataset'
3+
data_root = 'data/ade/ADEChallengeData2016'
4+
img_norm_cfg = dict(
5+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
6+
crop_size = (512, 512)
7+
train_pipeline = [
8+
dict(type='LoadImageFromFile'),
9+
dict(type='LoadAnnotations', reduce_zero_label=True),
10+
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
11+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
12+
dict(type='RandomFlip', prob=0.5),
13+
dict(type='PhotoMetricDistortion'),
14+
dict(type='Normalize', **img_norm_cfg),
15+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
16+
dict(type='DefaultFormatBundle'),
17+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
18+
]
19+
test_pipeline = [
20+
dict(type='LoadImageFromFile'),
21+
dict(
22+
type='MultiScaleFlipAug',
23+
img_scale=(2048, 512),
24+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
25+
flip=False,
26+
transforms=[
27+
dict(type='Resize', keep_ratio=True),
28+
dict(type='RandomFlip'),
29+
dict(type='Normalize', **img_norm_cfg),
30+
dict(type='ImageToTensor', keys=['img']),
31+
dict(type='Collect', keys=['img']),
32+
])
33+
]
34+
data = dict(
35+
samples_per_gpu=4,
36+
workers_per_gpu=4,
37+
train=dict(
38+
type=dataset_type,
39+
data_root=data_root,
40+
img_dir='images/training',
41+
ann_dir='annotations/training',
42+
pipeline=train_pipeline),
43+
val=dict(
44+
type=dataset_type,
45+
data_root=data_root,
46+
img_dir='images/validation',
47+
ann_dir='annotations/validation',
48+
pipeline=test_pipeline),
49+
test=dict(
50+
type=dataset_type,
51+
data_root=data_root,
52+
img_dir='images/validation',
53+
ann_dir='annotations/validation',
54+
pipeline=test_pipeline))

‎imseg/mmseg/_base_/datasets/ade20k_640x640.py

+54
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
# dataset settings
2+
dataset_type = 'ADE20KDataset'
3+
data_root = 'data/ade/ADEChallengeData2016'
4+
img_norm_cfg = dict(
5+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
6+
crop_size = (640, 640)
7+
train_pipeline = [
8+
dict(type='LoadImageFromFile'),
9+
dict(type='LoadAnnotations', reduce_zero_label=True),
10+
dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)),
11+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
12+
dict(type='RandomFlip', prob=0.5),
13+
dict(type='PhotoMetricDistortion'),
14+
dict(type='Normalize', **img_norm_cfg),
15+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
16+
dict(type='DefaultFormatBundle'),
17+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
18+
]
19+
test_pipeline = [
20+
dict(type='LoadImageFromFile'),
21+
dict(
22+
type='MultiScaleFlipAug',
23+
img_scale=(2560, 640),
24+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
25+
flip=False,
26+
transforms=[
27+
dict(type='Resize', keep_ratio=True),
28+
dict(type='RandomFlip'),
29+
dict(type='Normalize', **img_norm_cfg),
30+
dict(type='ImageToTensor', keys=['img']),
31+
dict(type='Collect', keys=['img']),
32+
])
33+
]
34+
data = dict(
35+
samples_per_gpu=4,
36+
workers_per_gpu=4,
37+
train=dict(
38+
type=dataset_type,
39+
data_root=data_root,
40+
img_dir='images/training',
41+
ann_dir='annotations/training',
42+
pipeline=train_pipeline),
43+
val=dict(
44+
type=dataset_type,
45+
data_root=data_root,
46+
img_dir='images/validation',
47+
ann_dir='annotations/validation',
48+
pipeline=test_pipeline),
49+
test=dict(
50+
type=dataset_type,
51+
data_root=data_root,
52+
img_dir='images/validation',
53+
ann_dir='annotations/validation',
54+
pipeline=test_pipeline))

‎imseg/mmseg/_base_/datasets/chase_db1.py

+59
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
1+
# dataset settings
2+
dataset_type = 'ChaseDB1Dataset'
3+
data_root = 'data/CHASE_DB1'
4+
img_norm_cfg = dict(
5+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
6+
img_scale = (960, 999)
7+
crop_size = (128, 128)
8+
train_pipeline = [
9+
dict(type='LoadImageFromFile'),
10+
dict(type='LoadAnnotations'),
11+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
12+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
13+
dict(type='RandomFlip', prob=0.5),
14+
dict(type='PhotoMetricDistortion'),
15+
dict(type='Normalize', **img_norm_cfg),
16+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
17+
dict(type='DefaultFormatBundle'),
18+
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
19+
]
20+
test_pipeline = [
21+
dict(type='LoadImageFromFile'),
22+
dict(
23+
type='MultiScaleFlipAug',
24+
img_scale=img_scale,
25+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
26+
flip=False,
27+
transforms=[
28+
dict(type='Resize', keep_ratio=True),
29+
dict(type='RandomFlip'),
30+
dict(type='Normalize', **img_norm_cfg),
31+
dict(type='ImageToTensor', keys=['img']),
32+
dict(type='Collect', keys=['img'])
33+
])
34+
]
35+
36+
data = dict(
37+
samples_per_gpu=4,
38+
workers_per_gpu=4,
39+
train=dict(
40+
type='RepeatDataset',
41+
times=40000,
42+
dataset=dict(
43+
type=dataset_type,
44+
data_root=data_root,
45+
img_dir='images/training',
46+
ann_dir='annotations/training',
47+
pipeline=train_pipeline)),
48+
val=dict(
49+
type=dataset_type,
50+
data_root=data_root,
51+
img_dir='images/validation',
52+
ann_dir='annotations/validation',
53+
pipeline=test_pipeline),
54+
test=dict(
55+
type=dataset_type,
56+
data_root=data_root,
57+
img_dir='images/validation',
58+
ann_dir='annotations/validation',
59+
pipeline=test_pipeline))

‎imseg/mmseg/_base_/datasets/cityscapes.py

+54
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
# dataset settings
2+
dataset_type = 'CityscapesDataset'
3+
data_root = 'data/cityscapes/'
4+
img_norm_cfg = dict(
5+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
6+
crop_size = (512, 1024)
7+
train_pipeline = [
8+
dict(type='LoadImageFromFile'),
9+
dict(type='LoadAnnotations'),
10+
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
11+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
12+
dict(type='RandomFlip', prob=0.5),
13+
dict(type='PhotoMetricDistortion'),
14+
dict(type='Normalize', **img_norm_cfg),
15+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
16+
dict(type='DefaultFormatBundle'),
17+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
18+
]
19+
test_pipeline = [
20+
dict(type='LoadImageFromFile'),
21+
dict(
22+
type='MultiScaleFlipAug',
23+
img_scale=(2048, 1024),
24+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
25+
flip=False,
26+
transforms=[
27+
dict(type='Resize', keep_ratio=True),
28+
dict(type='RandomFlip'),
29+
dict(type='Normalize', **img_norm_cfg),
30+
dict(type='ImageToTensor', keys=['img']),
31+
dict(type='Collect', keys=['img']),
32+
])
33+
]
34+
data = dict(
35+
samples_per_gpu=2,
36+
workers_per_gpu=2,
37+
train=dict(
38+
type=dataset_type,
39+
data_root=data_root,
40+
img_dir='leftImg8bit/train',
41+
ann_dir='gtFine/train',
42+
pipeline=train_pipeline),
43+
val=dict(
44+
type=dataset_type,
45+
data_root=data_root,
46+
img_dir='leftImg8bit/val',
47+
ann_dir='gtFine/val',
48+
pipeline=test_pipeline),
49+
test=dict(
50+
type=dataset_type,
51+
data_root=data_root,
52+
img_dir='leftImg8bit/val',
53+
ann_dir='gtFine/val',
54+
pipeline=test_pipeline))

‎imseg/mmseg/_base_/datasets/cityscapes_1024x1024.py

+35
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
_base_ = './cityscapes.py'
2+
img_norm_cfg = dict(
3+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
4+
crop_size = (1024, 1024)
5+
train_pipeline = [
6+
dict(type='LoadImageFromFile'),
7+
dict(type='LoadAnnotations'),
8+
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
9+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
10+
dict(type='RandomFlip', prob=0.5),
11+
dict(type='PhotoMetricDistortion'),
12+
dict(type='Normalize', **img_norm_cfg),
13+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
14+
dict(type='DefaultFormatBundle'),
15+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
16+
]
17+
test_pipeline = [
18+
dict(type='LoadImageFromFile'),
19+
dict(
20+
type='MultiScaleFlipAug',
21+
img_scale=(2048, 1024),
22+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
23+
flip=False,
24+
transforms=[
25+
dict(type='Resize', keep_ratio=True),
26+
dict(type='RandomFlip'),
27+
dict(type='Normalize', **img_norm_cfg),
28+
dict(type='ImageToTensor', keys=['img']),
29+
dict(type='Collect', keys=['img']),
30+
])
31+
]
32+
data = dict(
33+
train=dict(pipeline=train_pipeline),
34+
val=dict(pipeline=test_pipeline),
35+
test=dict(pipeline=test_pipeline))

‎imseg/mmseg/_base_/datasets/cityscapes_768x768.py

+35
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
_base_ = './cityscapes.py'
2+
img_norm_cfg = dict(
3+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
4+
crop_size = (768, 768)
5+
train_pipeline = [
6+
dict(type='LoadImageFromFile'),
7+
dict(type='LoadAnnotations'),
8+
dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
9+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
10+
dict(type='RandomFlip', prob=0.5),
11+
dict(type='PhotoMetricDistortion'),
12+
dict(type='Normalize', **img_norm_cfg),
13+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
14+
dict(type='DefaultFormatBundle'),
15+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
16+
]
17+
test_pipeline = [
18+
dict(type='LoadImageFromFile'),
19+
dict(
20+
type='MultiScaleFlipAug',
21+
img_scale=(2049, 1025),
22+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
23+
flip=False,
24+
transforms=[
25+
dict(type='Resize', keep_ratio=True),
26+
dict(type='RandomFlip'),
27+
dict(type='Normalize', **img_norm_cfg),
28+
dict(type='ImageToTensor', keys=['img']),
29+
dict(type='Collect', keys=['img']),
30+
])
31+
]
32+
data = dict(
33+
train=dict(pipeline=train_pipeline),
34+
val=dict(pipeline=test_pipeline),
35+
test=dict(pipeline=test_pipeline))

‎imseg/mmseg/_base_/datasets/cityscapes_769x769.py

+35
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
_base_ = './cityscapes.py'
2+
img_norm_cfg = dict(
3+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
4+
crop_size = (769, 769)
5+
train_pipeline = [
6+
dict(type='LoadImageFromFile'),
7+
dict(type='LoadAnnotations'),
8+
dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
9+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
10+
dict(type='RandomFlip', prob=0.5),
11+
dict(type='PhotoMetricDistortion'),
12+
dict(type='Normalize', **img_norm_cfg),
13+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
14+
dict(type='DefaultFormatBundle'),
15+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
16+
]
17+
test_pipeline = [
18+
dict(type='LoadImageFromFile'),
19+
dict(
20+
type='MultiScaleFlipAug',
21+
img_scale=(2049, 1025),
22+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
23+
flip=False,
24+
transforms=[
25+
dict(type='Resize', keep_ratio=True),
26+
dict(type='RandomFlip'),
27+
dict(type='Normalize', **img_norm_cfg),
28+
dict(type='ImageToTensor', keys=['img']),
29+
dict(type='Collect', keys=['img']),
30+
])
31+
]
32+
data = dict(
33+
train=dict(pipeline=train_pipeline),
34+
val=dict(pipeline=test_pipeline),
35+
test=dict(pipeline=test_pipeline))

0 commit comments

Comments
 (0)