Models:
- Name: mae-base_upernet_8xb2-amp-160k_ade20k-512x512
  In Collection: UPerNet
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 48.13
      mIoU(ms+flip): 48.7
  Config: configs/mae/mae-base_upernet_8xb2-amp-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - ViT-B
    - UPerNet
    Training Resources: 8x V100 GPUS
    Memory (GB): 9.96
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k/upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752.log.json
  Paper:
    Title: Masked Autoencoders Are Scalable Vision Learners
    URL: https://arxiv.org/abs/2111.06377
  Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.24.0/mmseg/models/backbones/mae.py#L46
  Framework: PyTorch