X_SSL_Net/tmp/VMamba-main/segmentation/configs/vit/metafile.yaml

Models:
- Name: vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 47.71
      mIoU(ms+flip): 49.51
  Config: configs/vit/vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - ViT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 9.2
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 46.75
      mIoU(ms+flip): 48.46
  Config: configs/vit/vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - ViT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 9.2
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 47.73
      mIoU(ms+flip): 49.95
  Config: configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - ViT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 9.21
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-s16_upernet_8xb2-80k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 42.96
      mIoU(ms+flip): 43.79
  Config: configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-S
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 4.68
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-s16_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 42.87
      mIoU(ms+flip): 43.79
  Config: configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-S
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 4.68
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 43.82
      mIoU(ms+flip): 45.07
  Config: configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-S
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 5.69
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 43.52
      mIoU(ms+flip): 45.01
  Config: configs/vit/vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-S
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 5.69
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-b16_upernet_8xb2-80k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.24
      mIoU(ms+flip): 46.73
  Config: configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 7.75
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-b16_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.36
      mIoU(ms+flip): 47.16
  Config: configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 7.75
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.46
      mIoU(ms+flip): 47.16
  Config: configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 9.21
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch
- Name: vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 45.37
      mIoU(ms+flip): 47.23
  Config: configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - DeiT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 9.21
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json
  Paper:
    Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
    URL: https://arxiv.org/pdf/2010.11929.pdf
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/vit.py#L98
  Framework: PyTorch