e2e_mask_rcnn_fbnet_xirb16d_dsmask_600.yaml

MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  BACKBONE:
    CONV_BODY: FBNet
  FBNET:
    ARCH: "xirb16d_dsmask"
    BN_TYPE: "bn"
    WIDTH_DIVISOR: 8
    DW_CONV_SKIP_BN: True
    DW_CONV_SKIP_RELU: True
    DET_HEAD_LAST_SCALE: 0.0
  RPN:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDE: (16, )
    BATCH_SIZE_PER_IMAGE: 256
    PRE_NMS_TOP_N_TRAIN: 6000
    PRE_NMS_TOP_N_TEST: 6000
    POST_NMS_TOP_N_TRAIN: 2000
    POST_NMS_TOP_N_TEST: 200
    RPN_HEAD: FBNet.rpn_head
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 256
  ROI_BOX_HEAD:
    POOLER_RESOLUTION: 6
    FEATURE_EXTRACTOR: FBNet.roi_head
    NUM_CLASSES: 81
  ROI_MASK_HEAD:
    POOLER_RESOLUTION: 6
    FEATURE_EXTRACTOR: FBNet.roi_head_mask
    PREDICTOR: "MaskRCNNConv1x1Predictor"
    RESOLUTION: 12
    SHARE_BOX_FEATURE_EXTRACTOR: False
  MASK_ON: True
DATASETS:
  TRAIN: ("coco_2014_train", "coco_2014_valminusminival")
  TEST: ("coco_2014_minival",)
SOLVER:
  BASE_LR: 0.06
  WARMUP_FACTOR: 0.1
  WEIGHT_DECAY: 0.0001
  STEPS: (60000, 80000)
  MAX_ITER: 90000
  IMS_PER_BATCH: 128  # for 8GPUs
# TEST:
#   IMS_PER_BATCH: 8
INPUT:
  MIN_SIZE_TRAIN: (600, )
  MAX_SIZE_TRAIN: 1000
  MIN_SIZE_TEST: 600
  MAX_SIZE_TEST: 1000
  PIXEL_MEAN: [103.53, 116.28, 123.675]
  PIXEL_STD: [57.375, 57.12, 58.395]