mmpretrain/configs/mixmim/metafile.yml

Collections:
  - Name: MixMIM
    Metadata:
      Architecture:
        - Attention Dropout
        - Convolution
        - Dense Connections
        - Dropout
        - GELU
        - Layer Normalization
        - Multi-Head Attention
        - Scaled Dot-Product Attention
        - Tanh Activation
    Paper:
      Title: 'MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation
        Learning'
      URL: https://arxiv.org/abs/2205.13137
    README: configs/mixmim/README.md
    Code:
      URL: https://github.com/open-mmlab/mmpretrain/blob/main/mmpretrain/models/backbones/mixmim.py
      Version: v1.0.0rc4

Models:
  - Name: mixmim_mixmim-base_16xb128-coslr-300e_in1k
    Metadata:
      Epochs: 300
      Batch Size: 2048
      FLOPs: 16351906816
      Parameters: 114665784
      Training Data: ImageNet-1k
    In Collection: MixMIM
    Results: null
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth
    Config: configs/mixmim/mixmim_mixmim-base_16xb128-coslr-300e_in1k.py
    Downstream:
      - mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k
  - Name: mixmim-base_mixmim-pre_8xb128-coslr-100e_in1k
    Metadata:
      Epochs: 100
      Batch Size: 1024
      FLOPs: 16351906816
      Parameters: 88344352
      Training Data: ImageNet-1k
    In Collection: MixMIM
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 84.63
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth
    Config: configs/mixmim/benchmarks/mixmim-base_8xb128-coslr-100e_in1k.py