Collections:
  - Name: BEiTv2
    Metadata:
      Architecture:
        - Attention Dropout
        - Convolution
        - Dense Connections
        - Dropout
        - GELU
        - Layer Normalization
        - Multi-Head Attention
        - Scaled Dot-Product Attention
        - Tanh Activation
    Paper:
      Title: 'BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers'
      URL: https://arxiv.org/abs/2208.06366
    README: configs/beitv2/README.md
    Code:
      URL: https://github.com/open-mmlab/mmclassification/blob/dev-1.x/mmcls/models/backbones/beit.py
      Version: v1.0.0rc4

Models:
  - Name: beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k
    Metadata:
      Epochs: 300
      Batch Size: 2048
      FLOPs: 17581223424
      Parameters: 192811376
      Training Data: ImageNet-1k
    In Collection: BEiTv2
    Results: null
    Weights: https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth
    Config: configs/beitv2/beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py
    Downstream:
      - beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k
  - Name: beit-base-p16_beitv2-pre_8xb128-coslr-100e_in1k
    Metadata:
      Epochs: 100
      Batch Size: 1024
      FLOPs: 17581219584
      Parameters: 86530984
      Training Data: ImageNet-1k
    In Collection: BEiTv2
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 85.0
    Weights: https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth
    Config: configs/beitv2/benchmarks/beit-base-p16_8xb128-coslr-100e_in1k.py
  - Name: beit-base-p16_beitv2-in21k-pre_3rdparty_in1k
    Metadata:
      FLOPs: 17581219584
      Parameters: 86530984
      Training Data:
        - ImageNet-21k
        - ImageNet-1k
    In Collection: BEiTv2
    Results:
      - Dataset: ImageNet-1k
        Task: Image Classification
        Metrics:
          Top 1 Accuracy: 86.47
          Top 5 Accuracy: 97.99
    Weights: https://download.openmmlab.com/mmclassification/v0/beit/beitv2-base_3rdparty_in1k_20221114-73e11905.pth
    Config: configs/beitv2/benchmarks/beit-base-p16_8xb64_in1k.py
    Converted From:
      Weights: https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_base_patch16_224_pt1k_ft21kto1k.pth
      Code: https://github.com/microsoft/unilm/tree/master/beit2