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

67
Seg_All_In_One_MMSeg/configs/danet/README.md Normal file
View File

@@ -0,0 +1,67 @@
# DANet
> [Dual Attention Network for Scene Segmentation](https://arxiv.org/abs/1809.02983)
## Introduction
<!-- [ALGORITHM] -->
<a href="https://github.com/junfu1115/DANet/">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76">Code Snippet</a>
## Abstract
<!-- [ABSTRACT] -->
In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the features at each position by a weighted sum of the features at all positions. Similar features would be related to each other regardless of their distances. Meanwhile, the channel attention module selectively emphasizes interdependent channel maps by integrating associated features among all channel maps. We sum the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. We achieve new state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset. In particular, a Mean IoU score of 81.5% on Cityscapes test set is achieved without using coarse data. We make the code and trained model publicly available at [this https URL](https://github.com/junfu1115/DANet).
<!-- [IMAGE] -->
<div align=center>
<img src="https://user-images.githubusercontent.com/24582831/142900467-f832fdb9-3b7d-47d3-8e80-e6ee9303bdfb.png" width="70%"/>
</div>
## Results and models
### Cityscapes
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| DANet | R-50-D8 | 512x1024 | 40000 | 7.4 | 2.66 | V100 | 78.74 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json) |
| DANet | R-101-D8 | 512x1024 | 40000 | 10.9 | 1.99 | V100 | 80.52 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json) |
| DANet | R-50-D8 | 769x769 | 40000 | 8.8 | 1.56 | V100 | 78.88 | 80.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json) |
| DANet | R-101-D8 | 769x769 | 40000 | 12.8 | 1.07 | V100 | 79.88 | 81.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json) |
| DANet | R-50-D8 | 512x1024 | 80000 | - | - | V100 | 79.34 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json) |
| DANet | R-101-D8 | 512x1024 | 80000 | - | - | V100 | 80.41 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json) |
| DANet | R-50-D8 | 769x769 | 80000 | - | - | V100 | 79.27 | 80.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json) |
| DANet | R-101-D8 | 769x769 | 80000 | - | - | V100 | 80.47 | 82.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json) |
### ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| DANet | R-50-D8 | 512x512 | 80000 | 11.5 | 21.20 | V100 | 41.66 | 42.90 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json) |
| DANet | R-101-D8 | 512x512 | 80000 | 15 | 14.18 | V100 | 43.64 | 45.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json) |
| DANet | R-50-D8 | 512x512 | 160000 | - | - | V100 | 42.45 | 43.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json) |
| DANet | R-101-D8 | 512x512 | 160000 | - | - | V100 | 44.17 | 45.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json) |
### Pascal VOC 2012 + Aug
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| DANet | R-50-D8 | 512x512 | 20000 | 6.5 | 20.94 | V100 | 74.45 | 75.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
| DANet | R-101-D8 | 512x512 | 20000 | 9.9 | 13.76 | V100 | 76.02 | 77.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
| DANet | R-50-D8 | 512x512 | 40000 | - | - | V100 | 76.37 | 77.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json) |
| DANet | R-101-D8 | 512x512 | 40000 | - | - | V100 | 76.51 | 77.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json) |
## Citation
```bibtex
@article{fu2018dual,
title={Dual Attention Network for Scene Segmentation},
author={Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang,and Hanqing Lu},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2019}
}
```

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb2-40k_cityscapes-512x1024.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb2-40k_cityscapes-769x769.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb2-80k_cityscapes-512x1024.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb2-80k_cityscapes-769x769.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb4-160k_ade20k-512x512.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb4-20k_voc12aug-512x512.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb4-40k_voc12aug-512x512.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
Seg_All_In_One_MMSeg/configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './danet_r50-d8_4xb4-80k_ade20k-512x512.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

7
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,7 @@
_base_ = [
'../_base_/models/danet_r50-d8.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
]
crop_size = (512, 1024)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)

12
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,12 @@
_base_ = [
'../_base_/models/danet_r50-d8.py',
'../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k.py'
]
crop_size = (769, 769)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(align_corners=True),
auxiliary_head=dict(align_corners=True),
test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))

7
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,7 @@
_base_ = [
'../_base_/models/danet_r50-d8.py', '../_base_/datasets/cityscapes.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]
crop_size = (512, 1024)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)

12
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,12 @@
_base_ = [
'../_base_/models/danet_r50-d8.py',
'../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_80k.py'
]
crop_size = (769, 769)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(align_corners=True),
auxiliary_head=dict(align_corners=True),
test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))

10
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,10 @@
_base_ = [
'../_base_/models/danet_r50-d8.py', '../_base_/datasets/ade20k.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
]
crop_size = (512, 512)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(num_classes=150),
auxiliary_head=dict(num_classes=150))

11
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/danet_r50-d8.py',
'../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_20k.py'
]
crop_size = (512, 512)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(num_classes=21),
auxiliary_head=dict(num_classes=21))

11
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/danet_r50-d8.py',
'../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k.py'
]
crop_size = (512, 512)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(num_classes=21),
auxiliary_head=dict(num_classes=21))

10
Seg_All_In_One_MMSeg/configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,10 @@
_base_ = [
'../_base_/models/danet_r50-d8.py', '../_base_/datasets/ade20k.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]
crop_size = (512, 512)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(num_classes=150),
auxiliary_head=dict(num_classes=150))

387
Seg_All_In_One_MMSeg/configs/danet/metafile.yaml Normal file
View File

@@ -0,0 +1,387 @@
Collections:
- Name: DANet
License: Apache License 2.0
Metadata:
Training Data:
- Cityscapes
- ADE20K
- Pascal VOC 2012 + Aug
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
README: configs/danet/README.md
Frameworks:
- PyTorch
Models:
- Name: danet_r50-d8_4xb2-40k_cityscapes-512x1024
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.74
Config: configs/danet/danet_r50-d8_4xb2-40k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 7.4
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb2-40k_cityscapes-512x1024
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 80.52
Config: configs/danet/danet_r101-d8_4xb2-40k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 10.9
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb2-40k_cityscapes-769x769
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.88
mIoU(ms+flip): 80.62
Config: configs/danet/danet_r50-d8_4xb2-40k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 8.8
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb2-40k_cityscapes-769x769
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.88
mIoU(ms+flip): 81.47
Config: configs/danet/danet_r101-d8_4xb2-40k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 12.8
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb2-80k_cityscapes-512x1024
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.34
Config: configs/danet/danet_r50-d8_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb2-80k_cityscapes-512x1024
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 80.41
Config: configs/danet/danet_r101-d8_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb2-80k_cityscapes-769x769
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.27
mIoU(ms+flip): 80.96
Config: configs/danet/danet_r50-d8_4xb2-80k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb2-80k_cityscapes-769x769
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 80.47
mIoU(ms+flip): 82.02
Config: configs/danet/danet_r101-d8_4xb2-80k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb4-80k_ade20k-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 41.66
mIoU(ms+flip): 42.9
Config: configs/danet/danet_r50-d8_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 11.5
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb4-80k_ade20k-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 43.64
mIoU(ms+flip): 45.19
Config: configs/danet/danet_r101-d8_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 15.0
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb4-160k_ade20k-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 42.45
mIoU(ms+flip): 43.25
Config: configs/danet/danet_r50-d8_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb4-160k_ade20k-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 44.17
mIoU(ms+flip): 45.02
Config: configs/danet/danet_r101-d8_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb4-20k_voc12aug-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 74.45
mIoU(ms+flip): 75.69
Config: configs/danet/danet_r50-d8_4xb4-20k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 6.5
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb4-20k_voc12aug-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 76.02
mIoU(ms+flip): 77.23
Config: configs/danet/danet_r101-d8_4xb4-20k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Memory (GB): 9.9
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r50-d8_4xb4-40k_voc12aug-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 76.37
mIoU(ms+flip): 77.29
Config: configs/danet/danet_r50-d8_4xb4-40k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-50-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch
- Name: danet_r101-d8_4xb4-40k_voc12aug-512x512
In Collection: DANet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 76.51
mIoU(ms+flip): 77.32
Config: configs/danet/danet_r101-d8_4xb4-40k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-101-D8
- DANet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json
Paper:
Title: Dual Attention Network for Scene Segmentation
URL: https://arxiv.org/abs/1809.02983
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/da_head.py#L76
Framework: PyTorch

103
Seg_All_In_One_MMSeg/configs/danet/my_danet_r50_Pre_g1-40k_check_4000_my_dataset_model-512x512-no_testslide.py Normal file
View File

@@ -0,0 +1,103 @@
_base_ = [
'../_base_/models/danet_r50-d8.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 = (512, 512)
data_preprocessor = dict(
size=(512, 512),
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=(512, 512),
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(
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,
),
)
test_cfg = dict(
crop_size=(512, 512),
)
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,
),
]