Base-RCNN-FPN-D2SA.yaml

MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  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: 60
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_FC: 2
    POOLER_RESOLUTION: 7
  ROI_MASK_HEAD:
    NAME: "MaskRCNNConvUpsampleHead"
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
DATASETS:
  TRAIN: ("d2sa_train_aug","d2sa_train")
  TEST: ("d2sa_val",)
SOLVER:
  IMS_PER_BATCH: 2
  BASE_LR: 0.005
  STEPS: (40000, 60000)
  MAX_ITER: 70000
  #OPT_TYPE: "SGD"
  #CHECKPOINT_PERIOD: 10000
TEST:
  EVAL_PERIOD: 20000
INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
  #MASK_FORMAT: "bitmask"
OUTPUT_DIR:
  TRAIN_VERSION: 'mask_rcnn_amodal_d2sa_res50_1x'
SEED: 1