Skip to content

Commit 62f70eb

Browse files
DerrickWang005Junjun2016
DerrickWang005
and
Junjun2016
authored
support coco stuff-10k/164k (open-mmlab#625)
* support coco stuff-10k/164k * update docs * fix docs * update docs * fix import lints * Update docs/dataset_prepare.md * Update docs/dataset_prepare.md * Update tools/convert_datasets/coco_stuff164k.py * Update tools/convert_datasets/coco_stuff10k.py * Update tools/convert_datasets/coco_stuff10k.py * Update tools/convert_datasets/coco_stuff10k.py * Update tools/convert_datasets/coco_stuff10k.py * Update coco_stuff.py fix the description of the dataset * Update dataset_prepare.md fix the doc tree of coco stuff 10k * Update coco_stuff10k.py fix img_dir * Update coco_stuff.py fix descriptions * Update coco_stuff164k.py fix out_dir * Update coco_stuff10k.py fix save file name * Update coco_stuff.py fix seg_map_suffix * Update dataset_prepare.md fix -p * Update dataset_prepare.md fix doc tree * modify coco stuff convertor * Remove redundant code * fix 164k convert bug * remove redundant comment * add deeplabv3 configs and more iterations * replace shutil.move with shtil.copyfile * Update deeplabv3_r50-d8_512x512_4x4_80k_coco_stuff10k.py fix wrong config * Update deeplabv3_r101-d8_512x512_4x4_80k_coco_stuff164k.py fix wrong config * fix wrong configs * fix wrong configs * fix wrong path for coco stuff 10k * fix convert bugs * fix seg_filename bug * when nproc=0, use track progress * rename configs: coco_stuff --> coco-stuff * add coco-stuff 10k and 164k to README.md * update configs * add deeplabv3 benchmark * add pspnet benchmark * remove redundant comma Co-authored-by: Junjun2016 <[email protected]>
1 parent 4e6f2eb commit 62f70eb

34 files changed

+1328
-1
lines changed

‎README.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -102,12 +102,15 @@ Supported datasets:
102102
- [x] [PASCAL VOC](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#pascal-voc)
103103
- [x] [ADE20K](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#ade20k)
104104
- [x] [Pascal Context](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#pascal-context)
105+
- [x] [COCO-Stuff 10k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#coco-stuff-10k)
106+
- [x] [COCO-Stuff 164k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#coco-stuff-164k)
105107
- [x] [CHASE_DB1](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#chase-db1)
106108
- [x] [DRIVE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#drive)
107109
- [x] [HRF](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#hrf)
108110
- [x] [STARE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#stare)
109111
- [x] [Dark Zurich](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#dark-zurich)
110112
- [x] [Nighttime Driving](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#nighttime-driving)
113+
- [x] [Nighttime Driving](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#nighttime-driving)
111114

112115
## Installation
113116

‎README_zh-CN.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -101,6 +101,8 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
101101
- [x] [PASCAL VOC](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#pascal-voc)
102102
- [x] [ADE20K](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#ade20k)
103103
- [x] [Pascal Context](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#pascal-context)
104+
- [x] [COCO-Stuff 10k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#coco-stuff-10k)
105+
- [x] [COCO-Stuff 164k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#coco-stuff-164k)
104106
- [x] [CHASE_DB1](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#chase-db1)
105107
- [x] [DRIVE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#drive)
106108
- [x] [HRF](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#hrf)

‎configs/_base_/datasets/coco-stuff10k.py‎

Lines changed: 57 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,57 @@
1+
# dataset settings
2+
dataset_type = 'COCOStuffDataset'
3+
data_root = 'data/coco_stuff10k'
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+
reduce_zero_label=True,
41+
img_dir='images/train2014',
42+
ann_dir='annotations/train2014',
43+
pipeline=train_pipeline),
44+
val=dict(
45+
type=dataset_type,
46+
data_root=data_root,
47+
reduce_zero_label=True,
48+
img_dir='images/test2014',
49+
ann_dir='annotations/test2014',
50+
pipeline=test_pipeline),
51+
test=dict(
52+
type=dataset_type,
53+
data_root=data_root,
54+
reduce_zero_label=True,
55+
img_dir='images/test2014',
56+
ann_dir='annotations/test2014',
57+
pipeline=test_pipeline))

‎configs/_base_/datasets/coco-stuff164k.py‎

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
# dataset settings
2+
dataset_type = 'COCOStuffDataset'
3+
data_root = 'data/coco_stuff164k'
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'),
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/train2017',
41+
ann_dir='annotations/train2017',
42+
pipeline=train_pipeline),
43+
val=dict(
44+
type=dataset_type,
45+
data_root=data_root,
46+
img_dir='images/val2017',
47+
ann_dir='annotations/val2017',
48+
pipeline=test_pipeline),
49+
test=dict(
50+
type=dataset_type,
51+
data_root=data_root,
52+
img_dir='images/val2017',
53+
ann_dir='annotations/val2017',
54+
pipeline=test_pipeline))

‎configs/_base_/schedules/schedule_320k.py‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
# optimizer
2+
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
3+
optimizer_config = dict()
4+
# learning policy
5+
lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
6+
# runtime settings
7+
runner = dict(type='IterBasedRunner', max_iters=320000)
8+
checkpoint_config = dict(by_epoch=False, interval=32000)
9+
evaluation = dict(interval=32000, metric='mIoU')

‎configs/deeplabv3/README.md‎

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -73,3 +73,23 @@
7373
| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
7474
| DeepLabV3 | R-101-D8 | 480x480 | 40000 | - | - | 52.61 | 54.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59_20210416_110332-cb08ea46.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_40k_pascal_context_59/deeplabv3_r101-d8_480x480_40k_pascal_context_59-20210416_110332.log.json) |
7575
| DeepLabV3 | R-101-D8 | 480x480 | 80000 | - | - | 52.46 | 54.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59_20210416_113002-26303993.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_480x480_80k_pascal_context_59/deeplabv3_r101-d8_480x480_80k_pascal_context_59-20210416_113002.log.json) |
76+
77+
### COCO-Stuff 10k
78+
79+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
80+
| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
81+
| DeepLabV3 | R-50-D8 | 512x512 | 20000 | 9.6 | 10.8 | 34.66 | 36.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-b35f789d.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json) |
82+
| DeepLabV3 | R-101-D8 | 512x512 | 20000 | 13.2 | 8.7 | 37.30 | 38.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025-c49752cb.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_20k_coco-stuff10k_20210821_043025.log.json) |
83+
| DeepLabV3 | R-50-D8 | 512x512 | 40000 | - | - | 35.73 | 37.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-dc76f3ff.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r50-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json) |
84+
| DeepLabV3 | R-101-D8 | 512x512 | 40000 | - | - | 37.81 | 38.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305-636cb433.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k/deeplabv3_r101-d8_512x512_4x4_40k_coco-stuff10k_20210821_043305.log.json) |
85+
86+
### COCO-Stuff 164k
87+
88+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
89+
| --------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
90+
| DeepLabV3 | R-50-D8 | 512x512 | 80000 | 9.6 | 10.8 | 39.38 | 40.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016-88675c24.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_80k_coco-stuff164k_20210709_163016.log.json) |
91+
| DeepLabV3 | R-101-D8 | 512x512 | 80000 | 13.2 | 8.7 | 40.87 | 41.50 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252-13600dc2.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_80k_coco-stuff164k_20210709_201252.log.json) |
92+
| DeepLabV3 | R-50-D8 | 512x512 | 160000 | - | - | 41.09 | 41.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016-49f2812b.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_160k_coco-stuff164k_20210709_163016.log.json) |
93+
| DeepLabV3 | R-101-D8 | 512x512 | 160000 | - | - | 41.82 | 42.49 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402-f035acfd.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_160k_coco-stuff164k_20210709_155402.log.json) |
94+
| DeepLabV3 | R-50-D8 | 512x512 | 320000 | - | - | 41.37 | 42.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403-51b21115.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r50-d8_512x512_4x4_320k_coco-stuff164k_20210709_155403.log.json) |
95+
| DeepLabV3 | R-101-D8 | 512x512 | 320000 | - | - | 42.61 | 43.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402-3cbca14d.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k/deeplabv3_r101-d8_512x512_4x4_320k_coco-stuff164k_20210709_155402.log.json) |

0 commit comments

Comments
 (0)