mask2former/configs/cityscapes/instance-segmentation/swin/maskformer2_swin_base_IN21k_384_bs16_90k.yaml

_BASE_: ../maskformer2_R50_bs16_90k.yaml
MODEL:
  BACKBONE:
    NAME: "D2SwinTransformer"
  SWIN:
    EMBED_DIM: 128
    DEPTHS: [2, 2, 18, 2]
    NUM_HEADS: [4, 8, 16, 32]
    WINDOW_SIZE: 12
    APE: False
    DROP_PATH_RATE: 0.3
    PATCH_NORM: True
    PRETRAIN_IMG_SIZE: 384
  WEIGHTS: "swin_base_patch4_window12_384_22k.pkl"
  PIXEL_MEAN: [123.675, 116.280, 103.530]
  PIXEL_STD: [58.395, 57.120, 57.375]