Collections:
  - Name: UPerNet
    Metadata:
      Training Data:
        - Cityscapes
        - Pascal VOC 2012 + Aug
        - ADE20K

Models:

  - Name: upernet_r50_512x1024_40k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 235.29
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 77.10
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_40k_cityscapes/upernet_r50_512x1024_40k_cityscapes_20200605_094827-aa54cb54.pth
    Config: configs/upernet/upernet_r50_512x1024_40k_cityscapes.py



  - Name: upernet_r101_512x1024_40k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 263.85
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 78.69
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_40k_cityscapes/upernet_r101_512x1024_40k_cityscapes_20200605_094933-ebce3b10.pth
    Config: configs/upernet/upernet_r101_512x1024_40k_cityscapes.py



  - Name: upernet_r50_769x769_40k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 568.18
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 77.98
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_40k_cityscapes/upernet_r50_769x769_40k_cityscapes_20200530_033048-92d21539.pth
    Config: configs/upernet/upernet_r50_769x769_40k_cityscapes.py



  - Name: upernet_r101_769x769_40k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 641.03
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 79.03
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_40k_cityscapes/upernet_r101_769x769_40k_cityscapes_20200530_040819-83c95d01.pth
    Config: configs/upernet/upernet_r101_769x769_40k_cityscapes.py



  - Name: upernet_r50_512x1024_80k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 235.29
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 78.19
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x1024_80k_cityscapes/upernet_r50_512x1024_80k_cityscapes_20200607_052207-848beca8.pth
    Config: configs/upernet/upernet_r50_512x1024_80k_cityscapes.py



  - Name: upernet_r101_512x1024_80k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 263.85
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 79.40
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x1024_80k_cityscapes/upernet_r101_512x1024_80k_cityscapes_20200607_002403-f05f2345.pth
    Config: configs/upernet/upernet_r101_512x1024_80k_cityscapes.py



  - Name: upernet_r50_769x769_80k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 568.18
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 79.39
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_769x769_80k_cityscapes/upernet_r50_769x769_80k_cityscapes_20200607_005107-82ae7d15.pth
    Config: configs/upernet/upernet_r50_769x769_80k_cityscapes.py



  - Name: upernet_r101_769x769_80k_cityscapes
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 641.03
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Cityscapes
        Metrics:
          mIoU: 80.10
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_769x769_80k_cityscapes/upernet_r101_769x769_80k_cityscapes_20200607_001014-082fc334.pth
    Config: configs/upernet/upernet_r101_769x769_80k_cityscapes.py



  - Name: upernet_r50_512x512_80k_ade20k
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 42.74
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: ADE20K
        Metrics:
          mIoU: 40.70
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_80k_ade20k/upernet_r50_512x512_80k_ade20k_20200614_144127-ecc8377b.pth
    Config: configs/upernet/upernet_r50_512x512_80k_ade20k.py



  - Name: upernet_r101_512x512_80k_ade20k
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 49.16
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: ADE20K
        Metrics:
          mIoU: 42.91
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_80k_ade20k/upernet_r101_512x512_80k_ade20k_20200614_185117-32e4db94.pth
    Config: configs/upernet/upernet_r101_512x512_80k_ade20k.py



  - Name: upernet_r50_512x512_160k_ade20k
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 42.74
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: ADE20K
        Metrics:
          mIoU: 42.05
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_160k_ade20k/upernet_r50_512x512_160k_ade20k_20200615_184328-8534de8d.pth
    Config: configs/upernet/upernet_r50_512x512_160k_ade20k.py



  - Name: upernet_r101_512x512_160k_ade20k
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 49.16
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: ADE20K
        Metrics:
          mIoU: 43.82
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_160k_ade20k/upernet_r101_512x512_160k_ade20k_20200615_161951-91b32684.pth
    Config: configs/upernet/upernet_r101_512x512_160k_ade20k.py



  - Name: upernet_r50_512x512_20k_voc12aug
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 43.16
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Pascal VOC 2012 + Aug
        Metrics:
          mIoU: 74.82
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_20k_voc12aug/upernet_r50_512x512_20k_voc12aug_20200617_165330-5b5890a7.pth
    Config: configs/upernet/upernet_r50_512x512_20k_voc12aug.py



  - Name: upernet_r101_512x512_20k_voc12aug
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 50.05
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Pascal VOC 2012 + Aug
        Metrics:
          mIoU: 77.10
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_20k_voc12aug/upernet_r101_512x512_20k_voc12aug_20200617_165629-f14e7f27.pth
    Config: configs/upernet/upernet_r101_512x512_20k_voc12aug.py



  - Name: upernet_r50_512x512_40k_voc12aug
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 43.16
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Pascal VOC 2012 + Aug
        Metrics:
          mIoU: 75.92
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r50_512x512_40k_voc12aug/upernet_r50_512x512_40k_voc12aug_20200613_162257-ca9bcc6b.pth
    Config: configs/upernet/upernet_r50_512x512_40k_voc12aug.py



  - Name: upernet_r101_512x512_40k_voc12aug
    In Collection: UPerNet
    Metadata:
      inference time (ms/im):
        - value: 50.05
          hardware: V100
          backend: PyTorch
          batch size: 1
          mode: FP32
    Results:
      - Task: Semantic Segmentation
        Dataset: Pascal VOC 2012 + Aug
        Metrics:
          mIoU: 77.43
    Weights: https://download.openmmlab.com/mmsegmentation/v0.5/upernet/upernet_r101_512x512_40k_voc12aug/upernet_r101_512x512_40k_voc12aug_20200613_163549-e26476ac.pth
    Config: configs/upernet/upernet_r101_512x512_40k_voc12aug.py