Collections:

- Name: bisenetv1

  Metadata:

    Training Data:

    - Cityscapes

    - COCO-Stuff 164k

  Paper:

    URL: https://arxiv.org/abs/1808.00897

    Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'

  README: configs/bisenetv1/README.md

  Code:

    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/backbones/bisenetv1.py#L266

    Version: v0.18.0

  Converted From:

    Code: https://github.com/ycszen/TorchSeg/tree/master/model/bisenet

Models:

- Name: bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes

  In Collection: bisenetv1

  Metadata:

    backbone: R-18-D32

    crop size: (1024,1024)

    lr schd: 160000

    inference time (ms/im):

    - value: 31.48

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (1024,1024)

    Training Memory (GB): 5.69

  Results:

  - Task: Semantic Segmentation

    Dataset: Cityscapes

    Metrics:

      mIoU: 74.44

      mIoU(ms+flip): 77.05

  Config: configs/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth

- Name: bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes

  In Collection: bisenetv1

  Metadata:

    backbone: R-18-D32

    crop size: (1024,1024)

    lr schd: 160000

    inference time (ms/im):

    - value: 31.48

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (1024,1024)

    Training Memory (GB): 5.69

  Results:

  - Task: Semantic Segmentation

    Dataset: Cityscapes

    Metrics:

      mIoU: 74.37

      mIoU(ms+flip): 76.91

  Config: configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth

- Name: bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes

  In Collection: bisenetv1

  Metadata:

    backbone: R-18-D32

    crop size: (1024,1024)

    lr schd: 160000

    inference time (ms/im):

    - value: 31.48

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (1024,1024)

    Training Memory (GB): 11.17

  Results:

  - Task: Semantic Segmentation

    Dataset: Cityscapes

    Metrics:

      mIoU: 75.16

      mIoU(ms+flip): 77.24

  Config: configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth

- Name: bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes

  In Collection: bisenetv1

  Metadata:

    backbone: R-50-D32

    crop size: (1024,1024)

    lr schd: 160000

    inference time (ms/im):

    - value: 129.7

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (1024,1024)

    Training Memory (GB): 15.39

  Results:

  - Task: Semantic Segmentation

    Dataset: Cityscapes

    Metrics:

      mIoU: 76.92

      mIoU(ms+flip): 78.87

  Config: configs/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth

- Name: bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes

  In Collection: bisenetv1

  Metadata:

    backbone: R-50-D32

    crop size: (1024,1024)

    lr schd: 160000

    inference time (ms/im):

    - value: 129.7

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (1024,1024)

    Training Memory (GB): 15.39

  Results:

  - Task: Semantic Segmentation

    Dataset: Cityscapes

    Metrics:

      mIoU: 77.68

      mIoU(ms+flip): 79.57

  Config: configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth

- Name: bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k

  In Collection: bisenetv1

  Metadata:

    backbone: R-18-D32

    crop size: (512,512)

    lr schd: 160000

  Results:

  - Task: Semantic Segmentation

    Dataset: COCO-Stuff 164k

    Metrics:

      mIoU: 25.45

      mIoU(ms+flip): 26.15

  Config: configs/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth

- Name: bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k

  In Collection: bisenetv1

  Metadata:

    backbone: R-18-D32

    crop size: (512,512)

    lr schd: 160000

    inference time (ms/im):

    - value: 13.47

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (512,512)

    Training Memory (GB): 6.33

  Results:

  - Task: Semantic Segmentation

    Dataset: COCO-Stuff 164k

    Metrics:

      mIoU: 28.55

      mIoU(ms+flip): 29.26

  Config: configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth

- Name: bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k

  In Collection: bisenetv1

  Metadata:

    backbone: R-50-D32

    crop size: (512,512)

    lr schd: 160000

  Results:

  - Task: Semantic Segmentation

    Dataset: COCO-Stuff 164k

    Metrics:

      mIoU: 29.82

      mIoU(ms+flip): 30.33

  Config: configs/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth

- Name: bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k

  In Collection: bisenetv1

  Metadata:

    backbone: R-50-D32

    crop size: (512,512)

    lr schd: 160000

    inference time (ms/im):

    - value: 30.67

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (512,512)

    Training Memory (GB): 9.28

  Results:

  - Task: Semantic Segmentation

    Dataset: COCO-Stuff 164k

    Metrics:

      mIoU: 34.88

      mIoU(ms+flip): 35.37

  Config: configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth

- Name: bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k

  In Collection: bisenetv1

  Metadata:

    backbone: R-101-D32

    crop size: (512,512)

    lr schd: 160000

  Results:

  - Task: Semantic Segmentation

    Dataset: COCO-Stuff 164k

    Metrics:

      mIoU: 31.14

      mIoU(ms+flip): 31.76

  Config: configs/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth

- Name: bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k

  In Collection: bisenetv1

  Metadata:

    backbone: R-101-D32

    crop size: (512,512)

    lr schd: 160000

    inference time (ms/im):

    - value: 39.6

      hardware: V100

      backend: PyTorch

      batch size: 1

      mode: FP32

      resolution: (512,512)

    Training Memory (GB): 10.36

  Results:

  - Task: Semantic Segmentation

    Dataset: COCO-Stuff 164k

    Metrics:

      mIoU: 37.38

      mIoU(ms+flip): 37.99

  Config: configs/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth