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

68
Seg_All_In_One_MMSeg/configs/gcnet/README.md Normal file
View File

@@ -0,0 +1,68 @@
# GCNet
> [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://arxiv.org/abs/1904.11492)
## Introduction
<!-- [ALGORITHM] -->
<a href="https://github.com/xvjiarui/GCNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10">Code Snippet</a>
## Abstract
<!-- [ABSTRACT] -->
The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an image. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further observe that this simplified design shares similar structure with Squeeze-Excitation Network (SENet). Hence we unify them into a three-step general framework for global context modeling. Within the general framework, we design a better instantiation, called the global context (GC) block, which is lightweight and can effectively model the global context. The lightweight property allows us to apply it for multiple layers in a backbone network to construct a global context network (GCNet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks. The code and configurations are released at [this https URL](https://github.com/xvjiarui/GCNet).
<!-- [IMAGE] -->
<div align=center>
<img src="https://user-images.githubusercontent.com/24582831/142901601-ad17922e-2538-4b48-9f51-84a57d44b12b.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 |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| GCNet | R-50-D8 | 512x1024 | 40000 | 5.8 | 3.93 | V100 | 77.69 | 78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json) |
| GCNet | R-101-D8 | 512x1024 | 40000 | 9.2 | 2.61 | V100 | 78.28 | 79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json) |
| GCNet | R-50-D8 | 769x769 | 40000 | 6.5 | 1.67 | V100 | 78.12 | 80.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json) |
| GCNet | R-101-D8 | 769x769 | 40000 | 10.5 | 1.13 | V100 | 78.95 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json) |
| GCNet | R-50-D8 | 512x1024 | 80000 | - | - | V100 | 78.48 | 80.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json) |
| GCNet | R-101-D8 | 512x1024 | 80000 | - | - | V100 | 79.03 | 79.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json) |
| GCNet | R-50-D8 | 769x769 | 80000 | - | - | V100 | 78.68 | 80.66 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json) |
| GCNet | R-101-D8 | 769x769 | 80000 | - | - | V100 | 79.18 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json) |
### ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| GCNet | R-50-D8 | 512x512 | 80000 | 8.5 | 23.38 | V100 | 41.47 | 42.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json) |
| GCNet | R-101-D8 | 512x512 | 80000 | 12 | 15.20 | V100 | 42.82 | 44.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json) |
| GCNet | R-50-D8 | 512x512 | 160000 | - | - | V100 | 42.37 | 43.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json) |
| GCNet | R-101-D8 | 512x512 | 160000 | - | - | V100 | 43.69 | 45.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json) |
### Pascal VOC 2012 + Aug
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| GCNet | R-50-D8 | 512x512 | 20000 | 5.8 | 23.35 | V100 | 76.42 | 77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json) |
| GCNet | R-101-D8 | 512x512 | 20000 | 9.2 | 14.80 | V100 | 77.41 | 78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json) |
| GCNet | R-50-D8 | 512x512 | 40000 | - | - | V100 | 76.24 | 77.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json) |
| GCNet | R-101-D8 | 512x512 | 40000 | - | - | V100 | 77.84 | 78.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json) |
## Citation
```bibtex
@inproceedings{cao2019gcnet,
title={Gcnet: Non-local networks meet squeeze-excitation networks and beyond},
author={Cao, Yue and Xu, Jiarui and Lin, Stephen and Wei, Fangyun and Hu, Han},
booktitle={Proceedings of the IEEE International Conference on Computer Vision Workshops},
pages={0--0},
year={2019}
}
```

2
Seg_All_In_One_MMSeg/configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,2 @@
_base_ = './gcnet_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/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,7 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,12 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,7 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py Normal file
View File

@@ -0,0 +1,12 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,10 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/gcnet_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/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,10 @@
_base_ = [
'../_base_/models/gcnet_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))

391
Seg_All_In_One_MMSeg/configs/gcnet/metafile.yaml Normal file
View File

@@ -0,0 +1,391 @@
Collections:
- Name: GCNet
License: Apache License 2.0
Metadata:
Training Data:
- Cityscapes
- ADE20K
- Pascal VOC 2012 + Aug
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
README: configs/gcnet/README.md
Frameworks:
- PyTorch
Models:
- Name: gcnet_r50-d8_4xb2-40k_cityscapes-512x1024
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 77.69
mIoU(ms+flip): 78.56
Config: configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 5.8
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb2-40k_cityscapes-512x1024
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.28
mIoU(ms+flip): 79.34
Config: configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 9.2
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb2-40k_cityscapes-769x769
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.12
mIoU(ms+flip): 80.09
Config: configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 6.5
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb2-40k_cityscapes-769x769
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.95
mIoU(ms+flip): 80.71
Config: configs/gcnet/gcnet_r101-d8_4xb2-40k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 10.5
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb2-80k_cityscapes-512x1024
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.48
mIoU(ms+flip): 80.01
Config: configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb2-80k_cityscapes-512x1024
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.03
mIoU(ms+flip): 79.84
Config: configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb2-80k_cityscapes-769x769
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.68
mIoU(ms+flip): 80.66
Config: configs/gcnet/gcnet_r50-d8_4xb2-80k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb2-80k_cityscapes-769x769
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.18
mIoU(ms+flip): 80.71
Config: configs/gcnet/gcnet_r101-d8_4xb2-80k_cityscapes-769x769.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb4-80k_ade20k-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 41.47
mIoU(ms+flip): 42.85
Config: configs/gcnet/gcnet_r50-d8_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 8.5
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb4-80k_ade20k-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 42.82
mIoU(ms+flip): 44.54
Config: configs/gcnet/gcnet_r101-d8_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 12.0
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb4-160k_ade20k-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 42.37
mIoU(ms+flip): 43.52
Config: configs/gcnet/gcnet_r50-d8_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb4-160k_ade20k-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 43.69
mIoU(ms+flip): 45.21
Config: configs/gcnet/gcnet_r101-d8_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb4-20k_voc12aug-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 76.42
mIoU(ms+flip): 77.51
Config: configs/gcnet/gcnet_r50-d8_4xb4-20k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 5.8
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb4-20k_voc12aug-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 77.41
mIoU(ms+flip): 78.56
Config: configs/gcnet/gcnet_r101-d8_4xb4-20k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Memory (GB): 9.2
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r50-d8_4xb4-40k_voc12aug-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 76.24
mIoU(ms+flip): 77.63
Config: configs/gcnet/gcnet_r50-d8_4xb4-40k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-50-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch
- Name: gcnet_r101-d8_4xb4-40k_voc12aug-512x512
In Collection: GCNet
Results:
Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 77.84
mIoU(ms+flip): 78.59
Config: configs/gcnet/gcnet_r101-d8_4xb4-40k_voc12aug-512x512.py
Metadata:
Training Data: Pascal VOC 2012 + Aug
Batch Size: 16
Architecture:
- R-101-D8
- GCNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json
Paper:
Title: 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond'
URL: https://arxiv.org/abs/1904.11492
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/gc_head.py#L10
Framework: PyTorch

105
Seg_All_In_One_MMSeg/configs/gcnet/my_gcnet_r50_r101_Pre_g1-40k_check_4000_my_dataset_model-512x1024-testslide.py Normal file
View File

@@ -0,0 +1,105 @@
_base_ = [
'../_base_/models/gcnet_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, 1024)
data_preprocessor = dict(
size=(512, 1024),
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/resnet101_v1c.pth',
backbone=dict(
depth=101,
),
data_preprocessor=dict(
size=(512, 1024),
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=True,
),
auxiliary_head=dict(
num_classes=36,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
align_corners=True,
),
)
test_cfg = dict(
mode='slide',
crop_size=(512, 1024),
stride=(341, 682),
)
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,
),
]