Collections:
- Name: KNet
  Metadata:
    Training Data:
    - ADE20K
  Paper:
    URL: https://arxiv.org/abs/2106.14855
    Title: 'K-Net: Towards Unified Image Segmentation'
  README: configs/knet/README.md
  Code:
    URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.23.0/mmseg/models/decode_heads/knet_head.py#L392
    Version: v0.23.0
  Converted From:
    Code: https://github.com/ZwwWayne/K-Net/
Models:
- Name: knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: R-50-D8
    crop size: (512,512)
    lr schd: 80000
    inference time (ms/im):
    - value: 51.98
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 7.01
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 43.6
      mIoU(ms+flip): 45.12
  Config: configs/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_fcn_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_043751-abcab920.pth
- Name: knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: R-50-D8
    crop size: (512,512)
    lr schd: 80000
    inference time (ms/im):
    - value: 49.9
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 6.98
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 44.18
      mIoU(ms+flip): 45.58
  Config: configs/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_pspnet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_054634-d2c72240.pth
- Name: knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: R-50-D8
    crop size: (512,512)
    lr schd: 80000
    inference time (ms/im):
    - value: 82.64
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 7.42
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.06
      mIoU(ms+flip): 46.11
  Config: configs/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_deeplabv3_r50-d8_8x2_512x512_adamw_80k_ade20k_20220228_041642-00c8fbeb.pth
- Name: knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: R-50-D8
    crop size: (512,512)
    lr schd: 80000
    inference time (ms/im):
    - value: 58.45
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 7.34
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 43.45
      mIoU(ms+flip): 44.07
  Config: configs/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_r50-d8_8x2_512x512_adamw_80k_ade20k_20220304_125657-215753b0.pth
- Name: knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: Swin-T
    crop size: (512,512)
    lr schd: 80000
    inference time (ms/im):
    - value: 64.27
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 7.57
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.84
      mIoU(ms+flip): 46.27
  Config: configs/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k_20220303_133059-7545e1dc.pth
- Name: knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: Swin-L
    crop size: (512,512)
    lr schd: 80000
    inference time (ms/im):
    - value: 120.63
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (512,512)
    Training Memory (GB): 13.5
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 52.05
      mIoU(ms+flip): 53.24
  Config: configs/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k_20220303_154559-d8da9a90.pth
- Name: knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k
  In Collection: KNet
  Metadata:
    backbone: Swin-L
    crop size: (640,640)
    lr schd: 80000
    inference time (ms/im):
    - value: 120.63
      hardware: V100
      backend: PyTorch
      batch size: 1
      mode: FP32
      resolution: (640,640)
    Training Memory (GB): 13.54
  Results:
  - Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 52.21
      mIoU(ms+flip): 53.34
  Config: configs/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k_20220301_220747-8787fc71.pth