mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[Fix] Fix typo `ADE20k` to `ADE20K` in metafile #1120

pull/1801/head
MengzhangLI 2021-12-09 15:37:07 +08:00 committed by GitHub
parent 24b4761d83
commit 2e4da3ea75
6 changed files with 21 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/mobilenet_v2/README.md
View File

@ -44,7 +44,7 @@ The MobileNetV2 architecture is based on an inverted residual structure where th
| DeepLabV3 | M-V2-D8 | 512x1024 | 80000 | 3.9 | 8.4 | 73.84 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-bef03590.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes/deeplabv3_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json) |
| DeepLabV3+ | M-V2-D8 | 512x1024 | 80000 | 5.1 | 8.4 | 75.20 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes_20200825_124836-d256dd4b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes-20200825_124836.log.json) |
### ADE20k
### ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

10
configs/mobilenet_v2/mobilenet_v2.yml
View File

@ -3,7 +3,7 @@ Collections:
Metadata:
Training Data:
- Cityscapes
- ADE20k
- ADE20K
Paper:
URL: https://arxiv.org/abs/1801.04381
Title: 'MobileNetV2: Inverted Residuals and Linear Bottlenecks'
@ -114,7 +114,7 @@ Models:
Training Memory (GB): 6.5
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 19.71
Config: configs/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k.py
@ -135,7 +135,7 @@ Models:
Training Memory (GB): 6.5
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 29.68
Config: configs/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k.py
@ -156,7 +156,7 @@ Models:
Training Memory (GB): 6.8
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 34.08
Config: configs/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k.py
@ -177,7 +177,7 @@ Models:
Training Memory (GB): 8.2
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 34.02
Config: configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k.py

2
configs/resnest/README.md
View File

@ -42,7 +42,7 @@ year={2020}
| DeepLabV3 | S-101-D8 | 512x1024 | 80000 | 11.9 | 1.88 | 79.67 | 80.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes_20200807_144429-b73c4270.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3_s101-d8_512x1024_80k_cityscapes/deeplabv3_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json) |
| DeepLabV3+ | S-101-D8 | 512x1024 | 80000 | 13.2 | 2.36 | 79.62 | 80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes_20200807_144429-1239eb43.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/resnest/deeplabv3plus_s101-d8_512x1024_80k_cityscapes/deeplabv3plus_s101-d8_512x1024_80k_cityscapes-20200807_144429.log.json) |
### ADE20k
### ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------: | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

10
configs/resnest/resnest.yml
View File

@ -3,7 +3,7 @@ Collections:
Metadata:
Training Data:
- Cityscapes
- ADE20k
- ADE20K
Paper:
URL: https://arxiv.org/abs/2004.08955
Title: 'ResNeSt: Split-Attention Networks'
@ -118,7 +118,7 @@ Models:
Training Memory (GB): 14.2
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 45.62
mIoU(ms+flip): 46.16
@ -140,7 +140,7 @@ Models:
Training Memory (GB): 14.2
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 45.44
mIoU(ms+flip): 46.28
@ -162,7 +162,7 @@ Models:
Training Memory (GB): 14.6
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 45.71
mIoU(ms+flip): 46.59
@ -184,7 +184,7 @@ Models:
Training Memory (GB): 16.2
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 46.47
mIoU(ms+flip): 47.27

2
configs/segformer/README.md
View File

@ -45,7 +45,7 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
## Results and models
### ADE20k
### ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------: | -------: | -------------- | ---: | ------------- | ------ | -------- |

16
configs/segformer/segformer.yml
View File

@ -2,7 +2,7 @@ Collections:
- Name: segformer
Metadata:
Training Data:
- ADE20k
- ADE20K
Paper:
URL: https://arxiv.org/abs/2105.15203
Title: resize image to multiple of 32, improve SegFormer by 0.5-1.0 mIoU.
@ -29,7 +29,7 @@ Models:
Training Memory (GB): 2.1
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 37.41
mIoU(ms+flip): 38.34
@ -51,7 +51,7 @@ Models:
Training Memory (GB): 2.6
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 40.97
mIoU(ms+flip): 42.54
@ -73,7 +73,7 @@ Models:
Training Memory (GB): 3.6
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 45.58
mIoU(ms+flip): 47.03
@ -95,7 +95,7 @@ Models:
Training Memory (GB): 4.8
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 47.82
mIoU(ms+flip): 48.81
@ -117,7 +117,7 @@ Models:
Training Memory (GB): 6.1
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 48.46
mIoU(ms+flip): 49.76
@ -139,7 +139,7 @@ Models:
Training Memory (GB): 7.2
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 49.13
mIoU(ms+flip): 50.22
@ -161,7 +161,7 @@ Models:
Training Memory (GB): 11.5
Results:
- Task: Semantic Segmentation
Dataset: ADE20k
Dataset: ADE20K
Metrics:
mIoU: 49.62
mIoU(ms+flip): 50.36