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

Models:
  - Name: mae_vit-base-p16_8xb512-amp-coslr-300e_in1k
    Metadata:
      Epochs: 300
      Batch Size: 4096
      FLOPs: 17581972224
      Parameters: 111907840
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
    Downstream:
      - vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
  - Name: mae_vit-base-p16_8xb512-amp-coslr-400e_in1k
    Metadata:
      Epochs: 400
      Batch Size: 4096
      FLOPs: 17581972224
      Parameters: 111907840
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py
    Downstream:
      - vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
  - Name: mae_vit-base-p16_8xb512-amp-coslr-800e_in1k
    Metadata:
      Epochs: 800
      Batch Size: 4096
      FLOPs: 17581972224
      Parameters: 111907840
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py
    Downstream:
      - vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
  - Name: mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k
    Metadata:
      Epochs: 1600
      Batch Size: 4096
      FLOPs: 17581972224
      Parameters: 111907840
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py
    Downstream:
      - vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
  - Name: mae_vit-large-p16_8xb512-amp-coslr-400e_in1k
    Metadata:
      Epochs: 400
      Batch Size: 4096
      FLOPs: 61603111936
      Parameters: 329541888
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py
    Downstream:
      - vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
  - Name: mae_vit-large-p16_8xb512-amp-coslr-800e_in1k
    Metadata:
      Epochs: 800
      Batch Size: 4096
      FLOPs: 61603111936
      Parameters: 329541888
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py
    Downstream:
      - vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
  - Name: mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k
    Metadata:
      Epochs: 1600
      Batch Size: 4096
      FLOPs: 61603111936
      Parameters: 329541888
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py
    Downstream:
      - vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
      - vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
  - Name: mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k
    Metadata:
      Epochs: 1600
      Batch Size: 4096
      FLOPs: 167400741120
      Parameters: 657074508
      Training Data: ImageNet-1k
    In Collection: MAE
    Results: null
    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
    Config: configs/mae/mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py
    Downstream:
      - vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
      - vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
  - Name: vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
    Metadata:
      Epochs: 100
      Batch Size: 1024
      FLOPs: 17581215744
      Parameters: 86566120
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 83.1
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
  - Name: vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
    Metadata:
      Epochs: 100
      Batch Size: 1024
      FLOPs: 17581215744
      Parameters: 86566120
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 83.3
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
  - Name: vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
    Metadata:
      Epochs: 100
      Batch Size: 1024
      FLOPs: 17581215744
      Parameters: 86566120
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 83.3
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
  - Name: vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
    Metadata:
      Epochs: 100
      Batch Size: 1024
      FLOPs: 17581215744
      Parameters: 86566120
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 83.5
    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
    Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
  - Name: vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 17581972992
      Parameters: 86567656
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 60.8
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 17581972992
      Parameters: 86567656
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 62.5
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 17581972992
      Parameters: 86567656
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 65.1
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 17581972992
      Parameters: 86567656
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 67.1
    Weights: null
    Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
    Metadata:
      Epochs: 50
      Batch Size: 1024
      FLOPs: 61602103296
      Parameters: 304324584
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 85.2
    Weights: null
    Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
  - Name: vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
    Metadata:
      Epochs: 50
      Batch Size: 1024
      FLOPs: 61602103296
      Parameters: 304324584
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 85.4
    Weights: null
    Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
  - Name: vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
    Metadata:
      Epochs: 50
      Batch Size: 1024
      FLOPs: 61602103296
      Parameters: 304324584
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 85.7
    Weights: null
    Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
  - Name: vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 61603112960
      Parameters: 304326632
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 70.7
    Weights: null
    Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 61603112960
      Parameters: 304326632
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 73.7
    Weights: null
    Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
    Metadata:
      Epochs: 90
      Batch Size: 16384
      FLOPs: 61603112960
      Parameters: 304326632
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 75.5
    Weights: null
    Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
  - Name: vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
    Metadata:
      Epochs: 50
      Batch Size: 1024
      FLOPs: 167399096320
      Parameters: 632043240
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 86.9
    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
    Config: configs/mae/benchmarks/vit-huge-p14_8xb128-coslr-50e_in1k.py
  - Name: vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
    Metadata:
      Epochs: 50
      Batch Size: 256
      FLOPs: 732131983360
      Parameters: 633026280
      Training Data: ImageNet-1k
    In Collection: MAE
    Results:
      - Task: Image Classification
        Dataset: ImageNet-1k
        Metrics:
          Top 1 Accuracy: 87.3
    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
    Config: configs/mae/benchmarks/vit-huge-p14_32xb8-coslr-50e_in1k-448px.py