mmselfsup/configs/selfsup/mae/metafile.yml

Collections:
  - Name: MAE
    Metadata:
      Training Data: ImageNet-1k
      Training Techniques:
        - AdamW
      Training Resources: 8x A100-80G GPUs
      Architecture:
        - ViT
    Paper:
        URL: https://arxiv.org/abs/2111.06377
        Title: "Masked Autoencoders Are Scalable Vision Learners"
    README: configs/selfsup/mae/README.md

Models:
  - Name: mae_vit-base-p16_8xb512-amp-coslr-300e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 300
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 60.8
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 100
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 83.1
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
  - Name: mae_vit-base-p16_8xb512-amp-coslr-400e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 400
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 62.5
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 100
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 83.3
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
  - Name: mae_vit-base-p16_8xb512-amp-coslr-800e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 800
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 65.1
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 100
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 83.3
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
  - Name: mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 1600
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 67.1
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 100
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 83.5
        Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
        Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth
  - Name: mae_vit-large-p16_8xb512-amp-coslr-400e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 400
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 70.7
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 50
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 85.2
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
  - Name: mae_vit-large-p16_8xb512-amp-coslr-800e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 800
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 73.7
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 50
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 85.4
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
  - Name: mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k
    In Collection: MAE
    Metadata:
      Epochs: 1600
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 90
          Batch Size: 16384
        Results:
          - Task: Linear Evaluation
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 75.5
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py
      - Type: Image Classification
        Metadata:
          Epochs: 50
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 85.7
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
  - Name: mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py
    In Collection: MAE
    Metadata:
      Epochs: 1600
      Batch Size: 4096
    Results: null
    Config: configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py.py
    Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth
    Downstream:
      - Type: Image Classification
        Metadata:
          Epochs: 50
          Batch Size: 1024
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 86.9
        Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
        Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth
      - Type: Image Classification
        Metadata:
          Epochs: 50
          Batch Size: 256
        Results:
          - Task: Fine-tuning
            Dataset: ImageNet-1k
            Metrics:
              Top 1 Accuracy: 87.3
        Config: configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py
        Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth