configs/BoxSup-C2_Lbase_CLIP_SwinB_896b32_4x.yaml

_BASE_: "Base-C2_L_R5021k_640b64_4x.yaml"
MODEL:
  ROI_BOX_HEAD:
    USE_ZEROSHOT_CLS: True
  WEIGHTS: "models/swin_base_patch4_window7_224_22k.pkl"
  BACKBONE:
    NAME: build_swintransformer_fpn_backbone
  SWIN:
    SIZE: B-22k
  FPN:
    IN_FEATURES: ["swin1", "swin2", "swin3"]
SOLVER:
  MAX_ITER: 180000
  IMS_PER_BATCH: 32
  BASE_LR: 0.0001
INPUT:
  TRAIN_SIZE: 896
DATASETS:
  TRAIN: ("lvis_v1_train_norare",)