Collections:
- Name: MaskFormer
  License: Apache License 2.0
  Metadata:
    Training Data:
    - Usage
    - ADE20K
  Paper:
    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
      Segmentation'
    URL: https://arxiv.org/abs/2107.06278
  README: configs/maskformer/README.md
  Frameworks:
  - PyTorch
Models:
- Name: maskformer_r50-d32_8xb2-160k_ade20k-512x512
  In Collection: MaskFormer
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 44.29
  Config: configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - R-50-D32
    - MaskFormer
    Training Resources: 8x 42.20 GPUS
    Memory (GB): 3.29
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json
  Paper:
    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
      Segmentation'
    URL: https://arxiv.org/abs/2107.06278
  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
  Framework: PyTorch
- Name: maskformer_r101-d32_8xb2-160k_ade20k-512x512
  In Collection: MaskFormer
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.11
  Config: configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - R-101-D32
    - MaskFormer
    Training Resources: 8x 34.90 GPUS
    Memory (GB): 4.12
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json
  Paper:
    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
      Segmentation'
    URL: https://arxiv.org/abs/2107.06278
  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
  Framework: PyTorch
- Name: maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512
  In Collection: MaskFormer
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 46.69
  Config: configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-T
    - MaskFormer
    Training Resources: 8x 40.53 GPUS
    Memory (GB): 3.73
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json
  Paper:
    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
      Segmentation'
    URL: https://arxiv.org/abs/2107.06278
  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
  Framework: PyTorch
- Name: maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512
  In Collection: MaskFormer
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 49.36
  Config: configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-S
    - MaskFormer
    Training Resources: 8x 26.98 GPUS
    Memory (GB): 5.33
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json
  Paper:
    Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
      Segmentation'
    URL: https://arxiv.org/abs/2107.06278
  Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
  Framework: PyTorch