_BASE_: ./maskformer2_R50_bs16_50ep.yaml MODEL: SEM_SEG_HEAD: NUM_CLASSES: 133 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 OUT_FEATURES: ["res2", "res3", "res4", "res5"] WEIGHTS: "swin_base_patch4_window12_384.pkl" PIXEL_MEAN: [123.675, 116.280, 103.530] PIXEL_STD: [58.395, 57.120, 57.375]