AUG:
  DETR: true
CACHE_DIR: /mnt/localdata/users/yupanhuang/cache/huggingface
CUDNN_BENCHMARK: false
DATALOADER:
  ASPECT_RATIO_GROUPING: true
  FILTER_EMPTY_ANNOTATIONS: false
  NUM_WORKERS: 4
  REPEAT_THRESHOLD: 0.0
  SAMPLER_TRAIN: TrainingSampler
DATASETS:
  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
  PROPOSAL_FILES_TEST: []
  PROPOSAL_FILES_TRAIN: []
  TEST:
  - publaynet_val
  TRAIN:
  - publaynet_train
GLOBAL:
  HACK: 1.0
ICDAR_DATA_DIR_TEST: ''
ICDAR_DATA_DIR_TRAIN: ''
INPUT:
  CROP:
    ENABLED: true
    SIZE:
    - 384
    - 600
    TYPE: absolute_range
  FORMAT: RGB
  MASK_FORMAT: polygon
  MAX_SIZE_TEST: 1333
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MIN_SIZE_TRAIN:
  - 480
  - 512
  - 544
  - 576
  - 608
  - 640
  - 672
  - 704
  - 736
  - 768
  - 800
  MIN_SIZE_TRAIN_SAMPLING: choice
  RANDOM_FLIP: horizontal
MODEL:
  ANCHOR_GENERATOR:
    ANGLES:
    - - -90
      - 0
      - 90
    ASPECT_RATIOS:
    - - 0.5
      - 1.0
      - 2.0
    NAME: DefaultAnchorGenerator
    OFFSET: 0.0
    SIZES:
    - - 32
    - - 64
    - - 128
    - - 256
    - - 512
  BACKBONE:
    FREEZE_AT: 2
    NAME: build_vit_fpn_backbone
  CONFIG_PATH: ''
  DEVICE: cuda
  FPN:
    FUSE_TYPE: sum
    IN_FEATURES:
    - layer3
    - layer5
    - layer7
    - layer11
    NORM: ''
    OUT_CHANNELS: 256
  IMAGE_ONLY: true
  KEYPOINT_ON: false
  LOAD_PROPOSALS: false
  MASK_ON: true
  MAX_LENGTH: 510
  META_ARCHITECTURE: VLGeneralizedRCNN
  PANOPTIC_FPN:
    COMBINE:
      ENABLED: true
      INSTANCES_CONFIDENCE_THRESH: 0.5
      OVERLAP_THRESH: 0.5
      STUFF_AREA_LIMIT: 4096
    INSTANCE_LOSS_WEIGHT: 1.0
  PIXEL_MEAN:
  - 127.5
  - 127.5
  - 127.5
  PIXEL_STD:
  - 127.5
  - 127.5
  - 127.5
  PROPOSAL_GENERATOR:
    MIN_SIZE: 0
    NAME: RPN
  RESNETS:
    DEFORM_MODULATED: false
    DEFORM_NUM_GROUPS: 1
    DEFORM_ON_PER_STAGE:
    - false
    - false
    - false
    - false
    DEPTH: 50
    NORM: FrozenBN
    NUM_GROUPS: 1
    OUT_FEATURES:
    - res4
    RES2_OUT_CHANNELS: 256
    RES5_DILATION: 1
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: true
    WIDTH_PER_GROUP: 64
  RETINANET:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_WEIGHTS: &id001
    - 1.0
    - 1.0
    - 1.0
    - 1.0
    FOCAL_LOSS_ALPHA: 0.25
    FOCAL_LOSS_GAMMA: 2.0
    IN_FEATURES:
    - p3
    - p4
    - p5
    - p6
    - p7
    IOU_LABELS:
    - 0
    - -1
    - 1
    IOU_THRESHOLDS:
    - 0.4
    - 0.5
    NMS_THRESH_TEST: 0.5
    NORM: ''
    NUM_CLASSES: 80
    NUM_CONVS: 4
    PRIOR_PROB: 0.01
    SCORE_THRESH_TEST: 0.05
    SMOOTH_L1_LOSS_BETA: 0.1
    TOPK_CANDIDATES_TEST: 1000
  ROI_BOX_CASCADE_HEAD:
    BBOX_REG_WEIGHTS:
    - - 10.0
      - 10.0
      - 5.0
      - 5.0
    - - 20.0
      - 20.0
      - 10.0
      - 10.0
    - - 30.0
      - 30.0
      - 15.0
      - 15.0
    IOUS:
    - 0.5
    - 0.6
    - 0.7
  ROI_BOX_HEAD:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS:
    - 10.0
    - 10.0
    - 5.0
    - 5.0
    CLS_AGNOSTIC_BBOX_REG: true
    CONV_DIM: 256
    FC_DIM: 1024
    NAME: FastRCNNConvFCHead
    NORM: ''
    NUM_CONV: 0
    NUM_FC: 2
    POOLER_RESOLUTION: 7
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
    SMOOTH_L1_BETA: 0.0
    TRAIN_ON_PRED_BOXES: false
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    IOU_LABELS:
    - 0
    - 1
    IOU_THRESHOLDS:
    - 0.5
    NAME: CascadeROIHeads
    NMS_THRESH_TEST: 0.5
    NUM_CLASSES: 5
    POSITIVE_FRACTION: 0.25
    PROPOSAL_APPEND_GT: true
    SCORE_THRESH_TEST: 0.05
  ROI_KEYPOINT_HEAD:
    CONV_DIMS:
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    LOSS_WEIGHT: 1.0
    MIN_KEYPOINTS_PER_IMAGE: 1
    NAME: KRCNNConvDeconvUpsampleHead
    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
    NUM_KEYPOINTS: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  ROI_MASK_HEAD:
    CLS_AGNOSTIC_MASK: false
    CONV_DIM: 256
    NAME: MaskRCNNConvUpsampleHead
    NORM: ''
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  RPN:
    BATCH_SIZE_PER_IMAGE: 256
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS: *id001
    BOUNDARY_THRESH: -1
    CONV_DIMS:
    - -1
    HEAD_NAME: StandardRPNHead
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    - p6
    IOU_LABELS:
    - 0
    - -1
    - 1
    IOU_THRESHOLDS:
    - 0.3
    - 0.7
    LOSS_WEIGHT: 1.0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOPK_TEST: 1000
    POST_NMS_TOPK_TRAIN: 2000
    PRE_NMS_TOPK_TEST: 1000
    PRE_NMS_TOPK_TRAIN: 2000
    SMOOTH_L1_BETA: 0.0
  SEM_SEG_HEAD:
    COMMON_STRIDE: 4
    CONVS_DIM: 128
    IGNORE_VALUE: 255
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    LOSS_WEIGHT: 1.0
    NAME: SemSegFPNHead
    NORM: GN
    NUM_CLASSES: 54
  VIT:
    DROP_PATH: 0.1
    IMG_SIZE:
    - 224
    - 224
    MODEL_KWARGS: '{}'
    NAME: layoutlmv3_base
    OUT_FEATURES:
    - layer3
    - layer5
    - layer7
    - layer11
    POS_TYPE: abs
  WEIGHTS: /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/model_final.pth
OUTPUT_DIR: /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/
PUBLAYNET_DATA_DIR_TEST: /mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/val
PUBLAYNET_DATA_DIR_TRAIN: /mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/train
SEED: 42
SOLVER:
  AMP:
    ENABLED: true
  BACKBONE_MULTIPLIER: 1.0
  BASE_LR: 0.0002
  BIAS_LR_FACTOR: 1.0
  CHECKPOINT_PERIOD: 2000
  CLIP_GRADIENTS:
    CLIP_TYPE: full_model
    CLIP_VALUE: 1.0
    ENABLED: true
    NORM_TYPE: 2.0
  GAMMA: 0.1
  GRADIENT_ACCUMULATION_STEPS: 1
  IMS_PER_BATCH: 32
  LR_SCHEDULER_NAME: WarmupCosineLR
  MAX_ITER: 60000
  MOMENTUM: 0.9
  NESTEROV: false
  OPTIMIZER: ADAMW
  REFERENCE_WORLD_SIZE: 0
  STEPS:
  - 30000
  WARMUP_FACTOR: 0.01
  WARMUP_ITERS: 1000
  WARMUP_METHOD: linear
  WEIGHT_DECAY: 0.05
  WEIGHT_DECAY_BIAS: null
  WEIGHT_DECAY_NORM: 0.0
TEST:
  AUG:
    ENABLED: false
    FLIP: true
    MAX_SIZE: 4000
    MIN_SIZES:
    - 400
    - 500
    - 600
    - 700
    - 800
    - 900
    - 1000
    - 1100
    - 1200
  DETECTIONS_PER_IMAGE: 100
  EVAL_PERIOD: 2000
  EXPECTED_RESULTS: []
  KEYPOINT_OKS_SIGMAS: []
  PRECISE_BN:
    ENABLED: false
    NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 0