[Enhancement] Add UPerNet r18 results (#1669)

* add r18 configs * update r18 city result * add configs * update results * rename files * fix lint
2022-06-21 10:47:30 +08:00 · 2022-06-21 10:47:30 +08:00 · 36984d98ba
parent f2ea015920
commit 36984d98ba
8 changed files with 164 additions and 0 deletions
--- a/configs/upernet/README.md
+++ b/configs/upernet/README.md
@ -40,10 +40,12 @@ Humans recognize the visual world at multiple levels: we effortlessly categorize

 | Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                     | download                                                                                                                                                                                                                                                                                                                                           |
 | ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-18     | 512x1024  |   40000 | 4.8      | 4.47           | 75.39 |          77.0 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r18_512x1024_40k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x1024_40k_cityscapes/upernet_r18_512x1024_40k_cityscapes_20220615_113231-12ee861d.pth) \|[log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x1024_40k_cityscapes/upernet_r18_512x1024_40k_cityscapes_20220615_113231.log.json)      |
 | UPerNet | R-50     | 512x1024  |   40000 | 6.4      | 4.25           | 77.10 |         78.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_512x1024_40k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827.log.json)     |
 | UPerNet | R-101    | 512x1024  |   40000 | 7.4      | 3.79           | 78.69 |         80.11 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933.log.json) |
 | UPerNet | R-50     | 769x769   |   40000 | 7.2      | 1.76           | 77.98 |         79.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_769x769_40k_cityscapes.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048.log.json)         |
 | UPerNet | R-101    | 769x769   |   40000 | 8.4      | 1.56           | 79.03 |         80.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_769x769_40k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819.log.json)     |
+| UPerNet | R-18     | 512x1024  |   80000 | -        | -              | 76.02 |         77.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r18_512x1024_80k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x1024_80k_cityscapes/upernet_r18_512x1024_80k_cityscapes_20220614_110712-c89a9188.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x1024_80k_cityscapes/upernet_r18_512x1024_80k_cityscapes_20220614_110712.log.json)     |
 | UPerNet | R-50     | 512x1024  |   80000 | -        | -              | 78.19 |         79.19 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_512x1024_80k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207.log.json)     |
 | UPerNet | R-101    | 512x1024  |   80000 | -        | -              | 79.40 |         80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403.log.json) |
 | UPerNet | R-50     | 769x769   |   80000 | -        | -              | 79.39 |         80.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_769x769_80k_cityscapes.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107.log.json)         |
@ -53,8 +55,10 @@ Humans recognize the visual world at multiple levels: we effortlessly categorize

 | Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                 | download                                                                                                                                                                                                                                                                                                                           |
 | ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-18     | 512x512   |   80000 | 6.6      | 24.76          | 38.76 |         39.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r18_512x512_80k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_80k_ade20k/upernet_r18_512x512_80k_ade20k_20220614_110319-22e81719.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_80k_ade20k/upernet_r18_512x512_80k_ade20k_20220614_110319.log.json)         |
 | UPerNet | R-50     | 512x512   |   80000 | 8.1      | 23.40          | 40.70 |         41.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_512x512_80k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127.log.json)         |
 | UPerNet | R-101    | 512x512   |   80000 | 9.1      | 20.34          | 42.91 |         43.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_512x512_80k_ade20k.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117.log.json)     |
+| UPerNet | R-18     | 512x512   |  160000 | -        | -              | 39.23 |         39.97 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r18_512x512_160k_ade20k.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_160k_ade20k/upernet_r18_512x512_160k_ade20k_20220615_113300-791c3f3e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_160k_ade20k/upernet_r18_512x512_160k_ade20k_20220615_113300.log.json)     |
 | UPerNet | R-50     | 512x512   |  160000 | -        | -              | 42.05 |         42.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_512x512_160k_ade20k.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328.log.json)     |
 | UPerNet | R-101    | 512x512   |  160000 | -        | -              | 43.82 |         44.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951.log.json) |

@ -62,7 +66,9 @@ Humans recognize the visual world at multiple levels: we effortlessly categorize

 | Method  | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                  | download                                                                                                                                                                                                                                                                                                                               |
 | ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| UPerNet | R-18     | 512x512   |   20000 | 4.8      | 25.80          |  72.9 |         74.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r18_512x512_20k_voc12aug.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_20k_voc12aug/upernet_r18_512x512_20k_voc12aug_20220614_123910-ed66e455.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_20k_voc12aug/upernet_r18_512x512_20k_voc12aug_20220614_123910.log.json)     |
 | UPerNet | R-50     | 512x512   |   20000 | 6.4      | 23.17          | 74.82 |         76.35 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_512x512_20k_voc12aug.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330.log.json)     |
 | UPerNet | R-101    | 512x512   |   20000 | 7.5      | 19.98          | 77.10 |         78.29 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629.log.json) |
+| UPerNet | R-18     | 512x512   |   40000 | -        | -              | 73.71 |         74.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r18_512x512_40k_voc12aug.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_40k_voc12aug/upernet_r18_512x512_40k_voc12aug_20220614_153605-fafeb868.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_40k_voc12aug/upernet_r18_512x512_40k_voc12aug_20220614_153605.log.json)     |
 | UPerNet | R-50     | 512x512   |   40000 | -        | -              | 75.92 |         77.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r50_512x512_40k_voc12aug.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257.log.json)     |
 | UPerNet | R-101    | 512x512   |   40000 | -        | -              | 77.43 |         78.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/upernet/upernet_r101_512x512_40k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549.log.json) |
--- a/configs/upernet/upernet.yml
+++ b/configs/upernet/upernet.yml
@ -15,6 +15,28 @@ Collections:
  Converted From:
    Code: https://github.com/CSAILVision/unifiedparsing
 Models:
+- Name: upernet_r18_512x1024_40k_cityscapes
+  In Collection: UPerNet
+  Metadata:
+    backbone: R-18
+    crop size: (512,1024)
+    lr schd: 40000
+    inference time (ms/im):
+    - value: 223.71
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,1024)
+    Training Memory (GB): 4.8
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 75.39
+      mIoU(ms+flip): 77.0
+  Config: configs/upernet/upernet_r18_512x1024_40k_cityscapes.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x1024_40k_cityscapes/upernet_r18_512x1024_40k_cityscapes_20220615_113231-12ee861d.pth
 - Name: upernet_r50_512x1024_40k_cityscapes
  In Collection: UPerNet
  Metadata:
@ -103,6 +125,20 @@ Models:
      mIoU(ms+flip): 80.77
  Config: configs/upernet/upernet_r101_769x769_40k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth
+- Name: upernet_r18_512x1024_80k_cityscapes
+  In Collection: UPerNet
+  Metadata:
+    backbone: R-18
+    crop size: (512,1024)
+    lr schd: 80000
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Cityscapes
+    Metrics:
+      mIoU: 76.02
+      mIoU(ms+flip): 77.38
+  Config: configs/upernet/upernet_r18_512x1024_80k_cityscapes.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x1024_80k_cityscapes/upernet_r18_512x1024_80k_cityscapes_20220614_110712-c89a9188.pth
 - Name: upernet_r50_512x1024_80k_cityscapes
  In Collection: UPerNet
  Metadata:
@ -159,6 +195,28 @@ Models:
      mIoU(ms+flip): 81.49
  Config: configs/upernet/upernet_r101_769x769_80k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth
+- Name: upernet_r18_512x512_80k_ade20k
+  In Collection: UPerNet
+  Metadata:
+    backbone: R-18
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 40.39
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 6.6
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 38.76
+      mIoU(ms+flip): 39.81
+  Config: configs/upernet/upernet_r18_512x512_80k_ade20k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_80k_ade20k/upernet_r18_512x512_80k_ade20k_20220614_110319-22e81719.pth
 - Name: upernet_r50_512x512_80k_ade20k
  In Collection: UPerNet
  Metadata:
@ -203,6 +261,20 @@ Models:
      mIoU(ms+flip): 43.96
  Config: configs/upernet/upernet_r101_512x512_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth
+- Name: upernet_r18_512x512_160k_ade20k
+  In Collection: UPerNet
+  Metadata:
+    backbone: R-18
+    crop size: (512,512)
+    lr schd: 160000
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 39.23
+      mIoU(ms+flip): 39.97
+  Config: configs/upernet/upernet_r18_512x512_160k_ade20k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_160k_ade20k/upernet_r18_512x512_160k_ade20k_20220615_113300-791c3f3e.pth
 - Name: upernet_r50_512x512_160k_ade20k
  In Collection: UPerNet
  Metadata:
@ -231,6 +303,28 @@ Models:
      mIoU(ms+flip): 44.85
  Config: configs/upernet/upernet_r101_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth
+- Name: upernet_r18_512x512_20k_voc12aug
+  In Collection: UPerNet
+  Metadata:
+    backbone: R-18
+    crop size: (512,512)
+    lr schd: 20000
+    inference time (ms/im):
+    - value: 38.76
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 4.8
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 72.9
+      mIoU(ms+flip): 74.71
+  Config: configs/upernet/upernet_r18_512x512_20k_voc12aug.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_20k_voc12aug/upernet_r18_512x512_20k_voc12aug_20220614_123910-ed66e455.pth
 - Name: upernet_r50_512x512_20k_voc12aug
  In Collection: UPerNet
  Metadata:
@ -275,6 +369,20 @@ Models:
      mIoU(ms+flip): 78.29
  Config: configs/upernet/upernet_r101_512x512_20k_voc12aug.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth
+- Name: upernet_r18_512x512_40k_voc12aug
+  In Collection: UPerNet
+  Metadata:
+    backbone: R-18
+    crop size: (512,512)
+    lr schd: 40000
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Pascal VOC 2012 + Aug
+    Metrics:
+      mIoU: 73.71
+      mIoU(ms+flip): 74.61
+  Config: configs/upernet/upernet_r18_512x512_40k_voc12aug.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r18_512x512_40k_voc12aug/upernet_r18_512x512_40k_voc12aug_20220614_153605-fafeb868.pth
 - Name: upernet_r50_512x512_40k_voc12aug
  In Collection: UPerNet
  Metadata:
--- a/configs/upernet/upernet_r18_512x1024_40k_cityscapes.py
+++ b/configs/upernet/upernet_r18_512x1024_40k_cityscapes.py
@ -0,0 +1,6 @@
+_base_ = './upernet_r50_512x1024_40k_cityscapes.py'
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(in_channels=[64, 128, 256, 512]),
+    auxiliary_head=dict(in_channels=256))
--- a/configs/upernet/upernet_r18_512x1024_80k_cityscapes.py
+++ b/configs/upernet/upernet_r18_512x1024_80k_cityscapes.py
@ -0,0 +1,6 @@
+_base_ = './upernet_r50_512x1024_80k_cityscapes.py'
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(in_channels=[64, 128, 256, 512]),
+    auxiliary_head=dict(in_channels=256))
--- a/configs/upernet/upernet_r18_512x512_160k_ade20k.py
+++ b/configs/upernet/upernet_r18_512x512_160k_ade20k.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=150),
+    auxiliary_head=dict(in_channels=256, num_classes=150))
--- a/configs/upernet/upernet_r18_512x512_20k_voc12aug.py
+++ b/configs/upernet/upernet_r18_512x512_20k_voc12aug.py
@ -0,0 +1,10 @@
+_base_ = [
+    '../_base_/models/upernet_r50.py',
+    '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_20k.py'
+]
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=21),
+    auxiliary_head=dict(in_channels=256, num_classes=21))
--- a/configs/upernet/upernet_r18_512x512_40k_voc12aug.py
+++ b/configs/upernet/upernet_r18_512x512_40k_voc12aug.py
@ -0,0 +1,10 @@
+_base_ = [
+    '../_base_/models/upernet_r50.py',
+    '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=21),
+    auxiliary_head=dict(in_channels=256, num_classes=21))
--- a/configs/upernet/upernet_r18_512x512_80k_ade20k.py
+++ b/configs/upernet/upernet_r18_512x512_80k_ade20k.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=150),
+    auxiliary_head=dict(in_channels=256, num_classes=150))