mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

[Fix] Fix Dataset Display on README.md (#1072)

Browse Source 
* fix dataset display on readme

* delete pytorch1.3.1

* change PyTorch 1.5.1 to 1.5or1.5.0

* change PyTorch 1.5.1 to 1.5.0

* change PyTorch 1.5.1 to 1.5.0

* fix cu102
This commit is contained in:
MengzhangLI 2021-11-26 01:40:29 +08:00 committed by GitHub
parent 48d4222412
commit fdc054614c
9 changed files with 59 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
.github/workflows/build.yml vendored
View File

@ -27,26 +27,23 @@ jobs:
strategy:
matrix:
python-version: [3.7]
torch: [1.3.1, 1.5.1, 1.6.0, 1.7.0, 1.8.0, 1.9.0]
torch: [1.5.1, 1.6.0, 1.7.0, 1.8.0, 1.9.0]
include:
- torch: 1.3.1
torchvision: 0.4.2
mmcv: "latest+torch1.3.0+cpu"
- torch: 1.5.1
torchvision: 0.6.1
mmcv: "latest+torch1.5.0+cpu"
mmcv: 1.5.0
- torch: 1.6.0
torchvision: 0.7.0
mmcv: "latest+torch1.6.0+cpu"
mmcv: 1.6.0
- torch: 1.7.0
torchvision: 0.8.1
mmcv: "latest+torch1.7.0+cpu"
mmcv: 1.7.0
- torch: 1.8.0
torchvision: 0.9.0
mmcv: "latest+torch1.8.0+cpu"
mmcv: 1.8.0
- torch: 1.9.0
torchvision: 0.10.0
mmcv: "latest+torch1.9.0+cpu"
mmcv: 1.9.0
steps:
- uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
@ -62,7 +59,7 @@ jobs:
run: pip install torch==${{matrix.torch}}+cpu torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/torch_stable.html
- name: Install MMCV
run: |
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cpu/torch${{matrix.torch}}/index.html
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cpu/torch${{matrix.mmcv}}/index.html
python -c 'import mmcv; print(mmcv.__version__)'
- name: Install unittest dependencies
run: |
@ -93,33 +90,28 @@ jobs:
python-version: [3.7]
torch:
[
1.3.1,
1.5.1+cu101,
1.6.0+cu101,
1.7.0+cu101,
1.8.0+cu101
]
include:
- torch: 1.3.1
torch_version: torch1.3.1
torchvision: 0.4.2
mmcv_link: "torch1.3.0"
- torch: 1.5.1+cu101
torch_version: torch1.5.1
torchvision: 0.6.1+cu101
mmcv_link: "torch1.5.0"
mmcv: 1.5.0
- torch: 1.6.0+cu101
torch_version: torch1.6.0
torchvision: 0.7.0+cu101
mmcv_link: "torch1.6.0"
mmcv: 1.6.0
- torch: 1.7.0+cu101
torch_version: torch1.7.0
torchvision: 0.8.1+cu101
mmcv_link: "torch1.7.0"
mmcv: 1.7.0
- torch: 1.8.0+cu101
torch_version: torch1.8.0
torchvision: 0.9.0+cu101
mmcv_link: "torch1.8.0"
mmcv: 1.8.0
steps:
- uses: actions/checkout@v2
@ -140,7 +132,7 @@ jobs:
- name: Install mmseg dependencies
run: |
python -V
python -m pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/${{matrix.mmcv_link}}/index.html
python -m pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch${{matrix.mmcv}}/index.html
python -m pip install -r requirements.txt
python -c 'import mmcv; print(mmcv.__version__)'
- name: Build and install
@ -183,7 +175,7 @@ jobs:
- torch: 1.9.0+cu102
torch_version: torch1.9.0
torchvision: 0.10.0+cu102
mmcv_link: "torch1.9.0"
mmcv_link: 1.9.0
steps:
- uses: actions/checkout@v2
@ -204,7 +196,7 @@ jobs:
- name: Install mmseg dependencies
run: |
python -V
python -m pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu102/${{matrix.mmcv_link}}/index.html
python -m pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu102/torch${{matrix.mmcv_link}}/index.html
python -m pip install -r requirements.txt
python -c 'import mmcv; print(mmcv.__version__)'
- name: Build and install

3
README.md
View File

@ -21,7 +21,7 @@ English | [简体中文](README_zh-CN.md)
MMSegmentation is an open source semantic segmentation toolbox based on PyTorch.
It is a part of the OpenMMLab project.
The master branch works with **PyTorch 1.3+**.
The master branch works with **PyTorch 1.5+**.
![demo image](resources/seg_demo.gif)
@ -114,6 +114,7 @@ Supported datasets:
- [x] [STARE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#stare)
- [x] [Dark Zurich](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#dark-zurich)
- [x] [Nighttime Driving](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#nighttime-driving)
- [x] [LoveDA](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#loveda)
## Installation

27
README_zh-CN.md
View File

@ -20,7 +20,7 @@
MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 OpenMMLab 项目的一部分。
主分支代码目前支持 PyTorch 1.3 以上的版本。
主分支代码目前支持 PyTorch 1.5 以上的版本。
![示例图片](resources/seg_demo.gif)
@ -101,18 +101,19 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
已支持的数据集：
- [x] [Cityscapes](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#cityscapes)
- [x] [PASCAL VOC](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#pascal-voc)
- [x] [ADE20K](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#ade20k)
- [x] [Pascal Context](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#pascal-context)
- [x] [COCO-Stuff 10k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#coco-stuff-10k)
- [x] [COCO-Stuff 164k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#coco-stuff-164k)
- [x] [CHASE_DB1](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#chase-db1)
- [x] [DRIVE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#drive)
- [x] [HRF](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#hrf)
- [x] [STARE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#stare)
- [x] [Dark Zurich](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#dark-zurich)
- [x] [Nighttime Driving](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md#nighttime-driving)
- [x] [Cityscapes](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#cityscapes)
- [x] [PASCAL VOC](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#pascal-voc)
- [x] [ADE20K](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#ade20k)
- [x] [Pascal Context](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#pascal-context)
- [x] [COCO-Stuff 10k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#coco-stuff-10k)
- [x] [COCO-Stuff 164k](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#coco-stuff-164k)
- [x] [CHASE_DB1](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#chase-db1)
- [x] [DRIVE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#drive)
- [x] [HRF](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#hrf)
- [x] [STARE](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#stare)
- [x] [Dark Zurich](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#dark-zurich)
- [x] [Nighttime Driving](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#nighttime-driving)
- [x] [LoveDA](https://github.com/open-mmlab/mmsegmentation/blob/master/docs_zh-CN/dataset_prepare.md#loveda)
## 安装

8
configs/deeplabv3plus/README.md
View File

@ -62,7 +62,7 @@
| DeepLabV3+ | R-50-D8 | 512x512 | 160000 | - | - | 43.95 | 44.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504-6135c7e0.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_160k_ade20k/deeplabv3plus_r50-d8_512x512_160k_ade20k_20200615_124504.log.json) |
| DeepLabV3+ | R-101-D8 | 512x512 | 160000 | - | - | 45.47 | 46.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232-38ed86bb.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_160k_ade20k/deeplabv3plus_r101-d8_512x512_160k_ade20k_20200615_123232.log.json) |
#### Pascal VOC 2012 + Aug
### Pascal VOC 2012 + Aug
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
@ -71,21 +71,21 @@
| DeepLabV3+ | R-50-D8 | 512x512 | 40000 | - | - | 76.81 | 77.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759-e1b43aa9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_40k_voc12aug/deeplabv3plus_r50-d8_512x512_40k_voc12aug_20200613_161759.log.json) |
| DeepLabV3+ | R-101-D8 | 512x512 | 40000 | - | - | 78.62 | 79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333-faf03387.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_40k_voc12aug/deeplabv3plus_r101-d8_512x512_40k_voc12aug_20200613_205333.log.json) |
#### Pascal Context
### Pascal Context
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| DeepLabV3+ | R-101-D8 | 480x480 | 40000 | - | 9.09 | 47.30 | 48.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context_20200911_165459-d3c8a29e.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context/deeplabv3plus_r101-d8_480x480_40k_pascal_context-20200911_165459.log.json) |
| DeepLabV3+ | R-101-D8 | 480x480 | 80000 | - | - | 47.23 | 48.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context_20200911_155322-145d3ee8.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context/deeplabv3plus_r101-d8_480x480_80k_pascal_context-20200911_155322.log.json) |
#### Pascal Context 59
### Pascal Context 59
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| DeepLabV3+ | R-101-D8 | 480x480 | 40000 | - | - | 52.86 | 54.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json) |
| DeepLabV3+ | R-101-D8 | 480x480 | 80000 | - | - | 53.2 | 54.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json) |
#### LoveDA
### LoveDA
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

26
configs/deeplabv3plus/deeplabv3plus.yml
View File

@ -4,6 +4,10 @@ Collections:
Training Data:
- Cityscapes
- ADE20K
- Pascal VOC 2012 + Aug
- Pascal Context
- Pascal Context 59
- LoveDA
Paper:
URL: https://arxiv.org/abs/1802.02611
Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
@ -480,7 +484,7 @@ Models:
memory (GB): 7.6
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 75.93
mIoU(ms+flip): 77.5
@ -502,7 +506,7 @@ Models:
memory (GB): 11.0
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 77.22
mIoU(ms+flip): 78.59
@ -516,7 +520,7 @@ Models:
lr schd: 40000
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 76.81
mIoU(ms+flip): 77.57
@ -530,7 +534,7 @@ Models:
lr schd: 40000
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal VOC 2012 + Aug
Metrics:
mIoU: 78.62
mIoU(ms+flip): 79.53
@ -551,7 +555,7 @@ Models:
resolution: (480,480)
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal Context
Metrics:
mIoU: 47.3
mIoU(ms+flip): 48.47
@ -565,7 +569,7 @@ Models:
lr schd: 80000
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal Context
Metrics:
mIoU: 47.23
mIoU(ms+flip): 48.26
@ -579,7 +583,7 @@ Models:
lr schd: 40000
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal Context 59
Metrics:
mIoU: 52.86
mIoU(ms+flip): 54.54
@ -593,7 +597,7 @@ Models:
lr schd: 80000
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: Pascal Context 59
Metrics:
mIoU: 53.2
mIoU(ms+flip): 54.67
@ -615,7 +619,7 @@ Models:
memory (GB): 1.93
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: LoveDA
Metrics:
mIoU: 50.28
mIoU(ms+flip): 50.47
@ -637,7 +641,7 @@ Models:
memory (GB): 7.37
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: LoveDA
Metrics:
mIoU: 50.99
mIoU(ms+flip): 50.65
@ -659,7 +663,7 @@ Models:
memory (GB): 10.84
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Dataset: LoveDA
Metrics:
mIoU: 51.47
mIoU(ms+flip): 51.32

2
configs/hrnet/README.md
View File

@ -74,7 +74,7 @@
| FCN | HRNetV2p-W48 | 480x480 | 40000 | - | - | 50.33 | 52.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_40k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json) |
| FCN | HRNetV2p-W48 | 480x480 | 80000 | - | - | 51.12 | 53.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_80k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json) |
#### LoveDA
### LoveDA
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

7
configs/hrnet/hrnet.yml
View File

@ -7,6 +7,7 @@ Collections:
- Pascal VOC 2012 + Aug
- Pascal Context
- Pascal Context 59
- LoveDA
Paper:
URL: https://arxiv.org/abs/1908.07919
Title: Deep High-Resolution Representation Learning for Human Pose Estimation
@ -463,7 +464,7 @@ Models:
memory (GB): 1.72
Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59
Dataset: LoveDA
Metrics:
mIoU: 49.3
mIoU(ms+flip): 49.23
@ -485,7 +486,7 @@ Models:
memory (GB): 2.9
Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59
Dataset: LoveDA
Metrics:
mIoU: 50.87
mIoU(ms+flip): 51.24
@ -507,7 +508,7 @@ Models:
memory (GB): 6.25
Results:
- Task: Semantic Segmentation
Dataset: Pascal Context 59
Dataset: LoveDA
Metrics:
mIoU: 51.04
mIoU(ms+flip): 51.12

2
configs/pspnet/README.md
View File

@ -114,7 +114,7 @@ We support evaluation results on these two datasets using models above trained o
| PSPNet | R-50-D8 | 512x512 | 320000 | - | - | 40.53 | 40.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-be9610cc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r50-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json) |
| PSPNet | R-101-D8 | 512x512 | 320000 | - | - | 41.95 | 42.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004-72220c60.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k/pspnet_r101-d8_512x512_4x4_320k_coco-stuff164k_20210707_152004.log.json) |
#### LoveDA
### LoveDA
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

7
configs/pspnet/pspnet.yml
View File

@ -10,6 +10,7 @@ Collections:
- Dark Zurich and Nighttime Driving
- COCO-Stuff 10k
- COCO-Stuff 164k
- LoveDA
Paper:
URL: https://arxiv.org/abs/1612.01105
Title: Pyramid Scene Parsing Network
@ -757,7 +758,7 @@ Models:
memory (GB): 1.45
Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k
Dataset: LoveDA
Metrics:
mIoU: 48.62
mIoU(ms+flip): 47.57
@ -779,7 +780,7 @@ Models:
memory (GB): 6.14
Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k
Dataset: LoveDA
Metrics:
mIoU: 50.46
mIoU(ms+flip): 50.19
@ -801,7 +802,7 @@ Models:
memory (GB): 9.61
Results:
- Task: Semantic Segmentation
Dataset: COCO-Stuff 164k
Dataset: LoveDA
Metrics:
mIoU: 51.86
mIoU(ms+flip): 51.34