MODEL:
  META_ARCHITECTURE: "STAnything"
  MASK_ON: True
  VISUAL_PROMPT: True
  BACKBONE:
    FREEZE_AT: 0
    NAME: "build_resnet_backbone"
  WEIGHTS: "weights/bert_r50_coco.pth"
  PIXEL_MEAN: [123.675, 116.280, 103.530]
  PIXEL_STD: [58.395, 57.120, 57.375]
  RESNETS:
    DEPTH: 50
    STEM_TYPE: "basic"  # not used
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: False
    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
    # NORM: "SyncBN"
    RES5_MULTI_GRID: [1, 1, 1]  # not used
  SEM_SEG_HEAD:
    NAME: "MaskDINOHead"
    IGNORE_VALUE: 255
    NUM_CLASSES: 80
    LOSS_WEIGHT: 1.0
    CONVS_DIM: 256
    MASK_DIM: 256
    NORM: "GN"
    # pixel decoder
    PIXEL_DECODER_NAME: "MaskDINOEncoder"
    DIM_FEEDFORWARD: 1024
    NUM_FEATURE_LEVELS: 3
    TOTAL_NUM_FEATURE_LEVELS: 3
    IN_FEATURES: ["res2", "res3", "res4", "res5"]
    DEFORMABLE_TRANSFORMER_ENCODER_IN_FEATURES: ["res3", "res4", "res5"]
    COMMON_STRIDE: 4
    TRANSFORMER_ENC_LAYERS: 6
  MaskDINO:
    TRANSFORMER_DECODER_NAME: "MaskDINODecoder"
    DEEP_SUPERVISION: True
    NO_OBJECT_WEIGHT: 0.1
    CLASS_WEIGHT: 4.0
    MASK_WEIGHT: 5.0
    DICE_WEIGHT: 5.0
    BOX_WEIGHT: 5.0
    GIOU_WEIGHT: 2.0
    HIDDEN_DIM: 256
    NUM_OBJECT_QUERIES: 300
    NHEADS: 8
    DROPOUT: 0.0
    DIM_FEEDFORWARD: 2048
    ENC_LAYERS: 0
    PRE_NORM: False
    ENFORCE_INPUT_PROJ: False
    SIZE_DIVISIBILITY: 32
    DEC_LAYERS: 9  # 9+1, 9 decoder layers, add one for the loss on learnable query
    TRAIN_NUM_POINTS: 12544
    OVERSAMPLE_RATIO: 3.0
    IMPORTANCE_SAMPLE_RATIO: 0.75
    INITIAL_PRED: True
    TWO_STAGE: True
    DN: "standard"
    DN_NUM: 100
    INITIALIZE_BOX_TYPE: "no"
    TEST:
      SEMANTIC_ON: False
      INSTANCE_ON: True
      PANOPTIC_ON: False
      OVERLAP_THRESHOLD: 0.8
      OBJECT_MASK_THRESHOLD: 0.25
  TEXT:
    ARCH: clip_teacher
  LANGUAGE_BACKBONE:
    LANG_DIM: 512