dit-document-layout-analysis / Base-RCNN-FPN.yml
nielsr's picture
nielsr HF staff
Upload Base-RCNN-FPN.yml
d44ba07
MODEL:
MASK_ON: True
META_ARCHITECTURE: "GeneralizedRCNN"
PIXEL_MEAN: [123.675, 116.280, 103.530]
PIXEL_STD: [58.395, 57.120, 57.375]
BACKBONE:
NAME: "build_vit_fpn_backbone"
VIT:
OUT_FEATURES: ["layer3", "layer5", "layer7", "layer11"]
DROP_PATH: 0.1
IMG_SIZE: [224,224]
POS_TYPE: "abs"
FPN:
IN_FEATURES: ["layer3", "layer5", "layer7", "layer11"]
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: 5
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
ROI_MASK_HEAD:
NAME: "MaskRCNNConvUpsampleHead"
NUM_CONV: 4
POOLER_RESOLUTION: 14
DATASETS:
TRAIN: ("publaynet_train",)
TEST: ("publaynet_val",)
SOLVER:
LR_SCHEDULER_NAME: "WarmupCosineLR"
AMP:
ENABLED: True
OPTIMIZER: "ADAMW"
BACKBONE_MULTIPLIER: 1.0
CLIP_GRADIENTS:
ENABLED: True
CLIP_TYPE: "full_model"
CLIP_VALUE: 1.0
NORM_TYPE: 2.0
WARMUP_FACTOR: 0.01
BASE_LR: 0.0004
WEIGHT_DECAY: 0.05
IMS_PER_BATCH: 32
INPUT:
CROP:
ENABLED: True
TYPE: "absolute_range"
SIZE: (384, 600)
MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
FORMAT: "RGB"
DATALOADER:
FILTER_EMPTY_ANNOTATIONS: False
VERSION: 2
AUG:
DETR: True
SEED: 42