Collections:
- Name: Segformer
  Metadata:
    Training Data:
    - ADE20K
    - Cityscapes
  Paper:
    URL: https://arxiv.org/abs/2105.15203
    Title: 'SegFormer: Simple and Efficient Design for Semantic Segmentation with
      Transformers'
  README: configs/segformer/README.md
  Code:
    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/mit.py#L246
    Version: v0.17.0
  Converted From:
    Code: https://github.com/NVlabs/SegFormer
Models:
- Name: segformer_mit-b0_512x512_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B0
    crop size: (512,512)
    lr schd: 160000
    inference time (ms/im):
    - value: 19.49
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 2.1
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 37.41
      mIoU(ms+flip): 38.34
  Config: configs/segformer/segformer_mit-b0_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_512x512_160k_ade20k/segformer_mit-b0_512x512_160k_ade20k_20210726_101530-8ffa8fda.pth
- Name: segformer_mit-b1_512x512_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B1
    crop size: (512,512)
    lr schd: 160000
    inference time (ms/im):
    - value: 20.98
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 2.6
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 40.97
      mIoU(ms+flip): 42.54
  Config: configs/segformer/segformer_mit-b1_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_512x512_160k_ade20k/segformer_mit-b1_512x512_160k_ade20k_20210726_112106-d70e859d.pth
- Name: segformer_mit-b2_512x512_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B2
    crop size: (512,512)
    lr schd: 160000
    inference time (ms/im):
    - value: 32.38
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 3.6
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.58
      mIoU(ms+flip): 47.03
  Config: configs/segformer/segformer_mit-b2_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_512x512_160k_ade20k/segformer_mit-b2_512x512_160k_ade20k_20210726_112103-cbd414ac.pth
- Name: segformer_mit-b3_512x512_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B3
    crop size: (512,512)
    lr schd: 160000
    inference time (ms/im):
    - value: 45.23
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 4.8
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 47.82
      mIoU(ms+flip): 48.81
  Config: configs/segformer/segformer_mit-b3_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_512x512_160k_ade20k/segformer_mit-b3_512x512_160k_ade20k_20210726_081410-962b98d2.pth
- Name: segformer_mit-b4_512x512_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B4
    crop size: (512,512)
    lr schd: 160000
    inference time (ms/im):
    - value: 64.72
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 6.1
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 48.46
      mIoU(ms+flip): 49.76
  Config: configs/segformer/segformer_mit-b4_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_512x512_160k_ade20k/segformer_mit-b4_512x512_160k_ade20k_20210728_183055-7f509d7d.pth
- Name: segformer_mit-b5_512x512_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B5
    crop size: (512,512)
    lr schd: 160000
    inference time (ms/im):
    - value: 84.1
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 7.2
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 49.13
      mIoU(ms+flip): 50.22
  Config: configs/segformer/segformer_mit-b5_512x512_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_512x512_160k_ade20k/segformer_mit-b5_512x512_160k_ade20k_20210726_145235-94cedf59.pth
- Name: segformer_mit-b5_640x640_160k_ade20k
  In Collection: Segformer
  Metadata:
    backbone: MIT-B5
    crop size: (640,640)
    lr schd: 160000
    inference time (ms/im):
    - value: 88.5
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (640,640)
    Training Memory (GB): 11.5
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 49.62
      mIoU(ms+flip): 50.36
  Config: configs/segformer/segformer_mit-b5_640x640_160k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_640x640_160k_ade20k/segformer_mit-b5_640x640_160k_ade20k_20210801_121243-41d2845b.pth
- Name: segformer_mit-b0_8x1_1024x1024_160k_cityscapes
  In Collection: Segformer
  Metadata:
    backbone: MIT-B0
    crop size: (1024,1024)
    lr schd: 160000
    inference time (ms/im):
    - value: 210.97
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (1024,1024)
    Training Memory (GB): 3.64
  Results:
  - Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 76.54
      mIoU(ms+flip): 78.22
  Config: configs/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b0_8x1_1024x1024_160k_cityscapes/segformer_mit-b0_8x1_1024x1024_160k_cityscapes_20211208_101857-e7f88502.pth
- Name: segformer_mit-b1_8x1_1024x1024_160k_cityscapes
  In Collection: Segformer
  Metadata:
    backbone: MIT-B1
    crop size: (1024,1024)
    lr schd: 160000
    inference time (ms/im):
    - value: 232.56
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (1024,1024)
    Training Memory (GB): 4.49
  Results:
  - Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 78.56
      mIoU(ms+flip): 79.73
  Config: configs/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b1_8x1_1024x1024_160k_cityscapes/segformer_mit-b1_8x1_1024x1024_160k_cityscapes_20211208_064213-655c7b3f.pth
- Name: segformer_mit-b2_8x1_1024x1024_160k_cityscapes
  In Collection: Segformer
  Metadata:
    backbone: MIT-B2
    crop size: (1024,1024)
    lr schd: 160000
    inference time (ms/im):
    - value: 297.62
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (1024,1024)
    Training Memory (GB): 7.42
  Results:
  - Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 81.08
      mIoU(ms+flip): 82.18
  Config: configs/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b2_8x1_1024x1024_160k_cityscapes/segformer_mit-b2_8x1_1024x1024_160k_cityscapes_20211207_134205-6096669a.pth
- Name: segformer_mit-b3_8x1_1024x1024_160k_cityscapes
  In Collection: Segformer
  Metadata:
    backbone: MIT-B3
    crop size: (1024,1024)
    lr schd: 160000
    inference time (ms/im):
    - value: 395.26
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (1024,1024)
    Training Memory (GB): 10.86
  Results:
  - Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 81.94
      mIoU(ms+flip): 83.14
  Config: configs/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b3_8x1_1024x1024_160k_cityscapes/segformer_mit-b3_8x1_1024x1024_160k_cityscapes_20211206_224823-a8f8a177.pth
- Name: segformer_mit-b4_8x1_1024x1024_160k_cityscapes
  In Collection: Segformer
  Metadata:
    backbone: MIT-B4
    crop size: (1024,1024)
    lr schd: 160000
    inference time (ms/im):
    - value: 531.91
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (1024,1024)
    Training Memory (GB): 15.07
  Results:
  - Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 81.89
      mIoU(ms+flip): 83.38
  Config: configs/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b4_8x1_1024x1024_160k_cityscapes/segformer_mit-b4_8x1_1024x1024_160k_cityscapes_20211207_080709-07f6c333.pth
- Name: segformer_mit-b5_8x1_1024x1024_160k_cityscapes
  In Collection: Segformer
  Metadata:
    backbone: MIT-B5
    crop size: (1024,1024)
    lr schd: 160000
    inference time (ms/im):
    - value: 719.42
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (1024,1024)
    Training Memory (GB): 18.0
  Results:
  - Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 82.25
      mIoU(ms+flip): 83.48
  Config: configs/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segformer/segformer_mit-b5_8x1_1024x1024_160k_cityscapes/segformer_mit-b5_8x1_1024x1024_160k_cityscapes_20211206_072934-87a052ec.pth