metafile.yml

Collections:
  - Name: MViT V2
    Metadata:
      Architecture:
        - Attention Dropout
        - Convolution
        - Dense Connections
        - GELU
        - Layer Normalization
        - Scaled Dot-Product Attention
        - Attention Pooling
    Paper:
      URL: http://openaccess.thecvf.com//content/CVPR2022/papers/Li_MViTv2_Improved_Multiscale_Vision_Transformers_for_Classification_and_Detection_CVPR_2022_paper.pdf
      Title: 'MViTv2: Improved Multiscale Vision Transformers for Classification and Detection'
    README: configs/mvit/README.md
    Code:
      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.24.0/mmcls/models/backbones/mvit.py
      Version: v0.24.0

Models:
  - Name: mvitv2-tiny_3rdparty_in1k
    In Collection: MViT V2
    Metadata:
      FLOPs: 4703510768
      Parameters: 24173320
      Training Data:
        - ImageNet-1k
    Results:
    - Dataset: ImageNet-1k
      Task: Image Classification
      Metrics:
        Top 1 Accuracy: 82.33
        Top 5 Accuracy: 96.15
    Weights: https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-tiny_3rdparty_in1k_20220722-db7beeef.pth
    Converted From:
      Weights: https://dl.fbaipublicfiles.com/mvit/mvitv2_models/MViTv2_T_in1k.pyth
      Code: https://github.com/facebookresearch/mvit
    Config: configs/mvit/mvitv2-tiny_8xb256_in1k.py

  - Name: mvitv2-small_3rdparty_in1k
    In Collection: MViT V2
    Metadata:
      FLOPs: 6997555136
      Parameters: 34870216
      Training Data:
        - ImageNet-1k
    Results:
    - Dataset: ImageNet-1k
      Task: Image Classification
      Metrics:
        Top 1 Accuracy: 83.63
        Top 5 Accuracy: 96.51
    Weights: https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-small_3rdparty_in1k_20220722-986bd741.pth
    Converted From:
      Weights: https://dl.fbaipublicfiles.com/mvit/mvitv2_models/MViTv2_S_in1k.pyth
      Code: https://github.com/facebookresearch/mvit
    Config: configs/mvit/mvitv2-small_8xb256_in1k.py

  - Name: mvitv2-base_3rdparty_in1k
    In Collection: MViT V2
    Metadata:
      FLOPs: 10157964400
      Parameters: 51472744
      Training Data:
        - ImageNet-1k
    Results:
    - Dataset: ImageNet-1k
      Task: Image Classification
      Metrics:
        Top 1 Accuracy: 84.34
        Top 5 Accuracy: 96.86
    Weights: https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-base_3rdparty_in1k_20220722-9c4f0a17.pth
    Converted From:
      Weights: https://dl.fbaipublicfiles.com/mvit/mvitv2_models/MViTv2_B_in1k.pyth
      Code: https://github.com/facebookresearch/mvit
    Config: configs/mvit/mvitv2-base_8xb256_in1k.py

  - Name: mvitv2-large_3rdparty_in1k
    In Collection: MViT V2
    Metadata:
      FLOPs: 43868151412
      Parameters: 217992952
      Training Data:
        - ImageNet-1k
    Results:
    - Dataset: ImageNet-1k
      Task: Image Classification
      Metrics:
        Top 1 Accuracy: 85.25
        Top 5 Accuracy: 97.14
    Weights: https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-large_3rdparty_in1k_20220722-2b57b983.pth
    Converted From:
      Weights: https://dl.fbaipublicfiles.com/mvit/mvitv2_models/MViTv2_L_in1k.pyth
      Code: https://github.com/facebookresearch/mvit
    Config: configs/mvit/mvitv2-large_8xb256_in1k.py