admin/Seg_Data_Server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
admin
2026-05-20 15:05:35 +08:00
commit ac09b26253
2048 changed files with 189478 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
Seg_All_In_One_MMSeg/configs/cgnet/README.md Normal file
View File

@@ -0,0 +1,46 @@
# CGNet
> [CGNet: A Light-weight Context Guided Network for Semantic Segmentation](https://arxiv.org/abs/1811.08201)
## Introduction
<!-- [ALGORITHM] -->
<a href="https://github.com/wutianyiRosun/CGNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187">Code Snippet</a>
## Abstract
<!-- [ABSTRACT] -->
The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters hence unsuitable for mobile devices, while other small memory footprint models follow the spirit of classification network and ignore the inherent characteristic of semantic segmentation. To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation. We first propose the Context Guided (CG) block, which learns the joint feature of both local feature and surrounding context, and further improves the joint feature with the global context. Based on the CG block, we develop CGNet which captures contextual information in all stages of the network and is specially tailored for increasing segmentation accuracy. CGNet is also elaborately designed to reduce the number of parameters and save memory footprint. Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing segmentation networks. Extensive experiments on Cityscapes and CamVid datasets verify the effectiveness of the proposed approach. Specifically, without any post-processing and multi-scale testing, the proposed CGNet achieves 64.8% mean IoU on Cityscapes with less than 0.5 M parameters. The source code for the complete system can be found at [this https URL](https://github.com/wutianyiRosun/CGNet).
<!-- [IMAGE] -->
<div align=center>
<img src="https://user-images.githubusercontent.com/24582831/142900351-89559574-79cc-4f57-8f69-5d88765ec38d.png" width="80%"/>
</div>
## Results and models
### Cityscapes
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| CGNet | M3N21 | 680x680 | 60000 | 7.5 | 30.51 | V100 | 65.63 | 68.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json) |
| CGNet | M3N21 | 512x1024 | 60000 | 8.3 | 31.14 | V100 | 68.27 | 70.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json) |
## Citation
```bibtext
@article{wu2020cgnet,
title={Cgnet: A light-weight context guided network for semantic segmentation},
author={Wu, Tianyi and Tang, Sheng and Zhang, Rui and Cao, Juan and Zhang, Yongdong},
journal={IEEE Transactions on Image Processing},
volume={30},
pages={1169--1179},
year={2020},
publisher={IEEE}
}
```

59
Seg_All_In_One_MMSeg/configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py Normal file
View File

@@ -0,0 +1,59 @@
_base_ = [
'../_base_/models/cgnet.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
# optimizer
optimizer = dict(type='Adam', lr=0.001, eps=1e-08, weight_decay=0.0005)
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
# learning policy
param_scheduler = [
dict(
type='PolyLR',
eta_min=1e-4,
power=0.9,
by_epoch=False,
begin=0,
end=60000)
]
# runtime settings
total_iters = 60000
train_cfg = dict(
type='IterBasedTrainLoop', max_iters=total_iters, val_interval=4000)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=50),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=4000),
sampler_seed=dict(type='DistSamplerSeedHook'))
crop_size = (680, 680)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='RandomResize',
scale=(2048, 1024),
ratio_range=(0.5, 2.0),
keep_ratio=True),
dict(type='RandomCrop', crop_size=crop_size),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSegInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
# add loading annotation after ``Resize`` because ground truth
# does not need to do resize data transform
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
]
train_dataloader = dict(
batch_size=8, num_workers=4, dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(
batch_size=1, num_workers=4, dataset=dict(pipeline=test_pipeline))
test_dataloader = val_dataloader

38
Seg_All_In_One_MMSeg/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,38 @@
_base_ = [
'../_base_/models/cgnet.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py'
]
# optimizer
optimizer = dict(type='Adam', lr=0.001, eps=1e-08, weight_decay=0.0005)
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
# learning policy
param_scheduler = [
dict(
type='PolyLR',
eta_min=1e-4,
power=0.9,
by_epoch=False,
begin=0,
end=60000)
]
# runtime settings
total_iters = 60000
train_cfg = dict(
type='IterBasedTrainLoop', max_iters=total_iters, val_interval=4000)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=50),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=4000),
sampler_seed=dict(type='DistSamplerSeedHook'))
crop_size = (512, 1024)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)
train_dataloader = dict(batch_size=8)
val_dataloader = dict(batch_size=1)
test_dataloader = val_dataloader

61
Seg_All_In_One_MMSeg/configs/cgnet/metafile.yaml Normal file
View File

@@ -0,0 +1,61 @@
Collections:
- Name: CGNet
License: Apache License 2.0
Metadata:
Training Data:
- Cityscapes
Paper:
Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
URL: https://arxiv.org/abs/1811.08201
README: configs/cgnet/README.md
Frameworks:
- PyTorch
Models:
- Name: cgnet_fcn_4xb4-60k_cityscapes-680x680
In Collection: CGNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 65.63
mIoU(ms+flip): 68.04
Config: configs/cgnet/cgnet_fcn_4xb4-60k_cityscapes-680x680.py
Metadata:
Training Data: Cityscapes
Batch Size: 16
Architecture:
- M3N21
- CGNet
Training Resources: 4x V100 GPUS
Memory (GB): 7.5
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes_20201101_110253-4c0b2f2d.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_680x680_60k_cityscapes/cgnet_680x680_60k_cityscapes-20201101_110253.log.json
Paper:
Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
URL: https://arxiv.org/abs/1811.08201
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187
Framework: PyTorch
- Name: cgnet_fcn_4xb8-60k_cityscapes-512x1024
In Collection: CGNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 68.27
mIoU(ms+flip): 70.33
Config: configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 32
Architecture:
- M3N21
- CGNet
Training Resources: 4x V100 GPUS
Memory (GB): 8.3
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes_20201101_110254-124ea03b.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/cgnet/cgnet_512x1024_60k_cityscapes/cgnet_512x1024_60k_cityscapes-20201101_110254.log.json
Paper:
Title: 'CGNet: A Light-weight Context Guided Network for Semantic Segmentation'
URL: https://arxiv.org/abs/1811.08201
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/cgnet.py#L187
Framework: PyTorch

99
Seg_All_In_One_MMSeg/configs/cgnet/my_cgnet_fcn_fcn_g1-40k_check_4000_my_dataset_model-680x680.py Normal file
View File

@@ -0,0 +1,99 @@
_base_ = [
'../_base_/models/cgnet.py',
'../_base_/datasets/my_dataset_model.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k_check_4000.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (680, 680)
data_preprocessor = dict(
size=(680, 680),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
)
model = dict(
data_preprocessor=dict(
size=(680, 680),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='FCNHead',
in_channels=256,
in_index=2,
channels=256,
num_convs=0,
concat_input=False,
dropout_ratio=0,
num_classes=19,
norm_cfg=dict(
type='SyncBN',
eps=0.001,
requires_grad=True,
),
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
_delete_=True,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=False,
begin=0,
end=1500,
),
dict(
type='PolyLR',
power=0.9,
begin=1500,
end=40000,
eta_min=1e-05,
by_epoch=False,
),
]

84
Seg_All_In_One_MMSeg/configs/cgnet/my_cgnet_fcn_g1-40k_check_4000_my_dataset_model-680x680.py Normal file
View File

@@ -0,0 +1,84 @@
_base_ = [
'../_base_/models/cgnet.py',
'../_base_/datasets/my_dataset_model.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k_check_4000.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (680, 680)
data_preprocessor = dict(
size=(680, 680),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
)
model = dict(
data_preprocessor=dict(
size=(680, 680),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
),
decode_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=False,
begin=0,
end=1500,
),
dict(
type='PolyLR',
power=0.9,
begin=1500,
end=40000,
eta_min=1e-05,
by_epoch=False,
),
]

100
Seg_All_In_One_MMSeg/configs/cgnet/my_cgnet_r50_Pre_g1-40k_check_4000_my_dataset_model-680x680.py Normal file
View File

@@ -0,0 +1,100 @@
_base_ = [
'../_base_/models/cgnet.py',
'../_base_/datasets/my_dataset_model.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k_check_4000.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (680, 680)
data_preprocessor = dict(
size=(680, 680),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
)
model = dict(
pretrained='./My_Local_Model/open_mmlab/resnet50_v1c.pth',
backbone=dict(
depth=50,
),
data_preprocessor=dict(
size=(680, 680),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
),
decode_head=dict(
num_classes=36,
loss_decode=dict(
_delete_ = True,
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
align_corners=False,
),
auxiliary_head=dict(
num_classes=36,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
align_corners=False,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=False,
begin=0,
end=1500,
),
dict(
type='PolyLR',
power=0.9,
begin=1500,
end=40000,
eta_min=1e-05,
by_epoch=False,
),
]