MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  BACKBONE:
    NAME: "build_resnet_fpn_backbone"
  RESNETS:
    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
  FPN:
    IN_FEATURES: ["res2", "res3", "res4", "res5"]
  ANCHOR_GENERATOR:
    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
  RPN:
    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
    # Detectron1 uses 2000 proposals per-batch,
    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
    POST_NMS_TOPK_TRAIN: 1000
    POST_NMS_TOPK_TEST: 1000
  ROI_HEADS:
    NAME: "StandardROIHeads"
    IN_FEATURES: ["p2", "p3", "p4", "p5"]
    NUM_CLASSES: 1
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_FC: 2
    POOLER_RESOLUTION: 7
  ROI_MASK_HEAD:
    NAME: "MaskRCNNConvUpsampleHead"
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
DATASETS:
  TRAIN: ("base_coco_2017_train",)
  TEST: ("base_coco_2017_val", "densepose_chimps")
  CATEGORY_MAPS:
    "base_coco_2017_train":
      "16": 1 # bird -> person
      "17": 1 # cat -> person
      "18": 1 # dog -> person
      "19": 1 # horse -> person
      "20": 1 # sheep -> person
      "21": 1 # cow -> person
      "22": 1 # elephant -> person
      "23": 1 # bear -> person
      "24": 1 # zebra -> person
      "25": 1 # girafe -> person
    "base_coco_2017_val":
      "16": 1 # bird -> person
      "17": 1 # cat -> person
      "18": 1 # dog -> person
      "19": 1 # horse -> person
      "20": 1 # sheep -> person
      "21": 1 # cow -> person
      "22": 1 # elephant -> person
      "23": 1 # bear -> person
      "24": 1 # zebra -> person
      "25": 1 # girafe -> person
  WHITELISTED_CATEGORIES:
    "base_coco_2017_train":
      - 1  # person
      - 16 # bird
      - 17 # cat
      - 18 # dog
      - 19 # horse
      - 20 # sheep
      - 21 # cow
      - 22 # elephant
      - 23 # bear
      - 24 # zebra
      - 25 # girafe
    "base_coco_2017_val":
      - 1  # person
      - 16 # bird
      - 17 # cat
      - 18 # dog
      - 19 # horse
      - 20 # sheep
      - 21 # cow
      - 22 # elephant
      - 23 # bear
      - 24 # zebra
      - 25 # girafe
BOOTSTRAP_DATASETS:
  - DATASET: "chimpnsee"
    RATIO: 1.0
    IMAGE_LOADER:
      TYPE: "video_keyframe"
      SELECT:
        STRATEGY: "random_k"
        NUM_IMAGES: 4
      TRANSFORM:
        TYPE: "resize"
        MIN_SIZE: 800
        MAX_SIZE: 1333
      BATCH_SIZE: 8
      NUM_WORKERS: 1
    INFERENCE:
      INPUT_BATCH_SIZE: 1
      OUTPUT_BATCH_SIZE: 1
    DATA_SAMPLER:
      # supported types:
      #   densepose_uniform
      #   densepose_UV_confidence
      #   densepose_fine_segm_confidence
      #   densepose_coarse_segm_confidence
      TYPE: "densepose_uniform"
      COUNT_PER_CLASS: 8
    FILTER:
      TYPE: "detection_score"
      MIN_VALUE: 0.8
BOOTSTRAP_MODEL:
  WEIGHTS: ""
SOLVER:
  IMS_PER_BATCH: 16
  BASE_LR: 0.02
  STEPS: (60000, 80000)
  MAX_ITER: 90000
INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2