MaskTextSpotterV3-OCR / configs /mixtrain /seg_rec_poly_fuse_feature.yaml
3v324v23's picture
add
c310e19
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
# WEIGHT: './output/path-to-pretrain-model' # for training
WEIGHT: './output/mixtrain/trained_model.pth' # for testing
BACKBONE:
CONV_BODY: "R-50-FPN"
OUT_CHANNELS: 256
RESNETS:
BACKBONE_OUT_CHANNELS: 256
RPN:
USE_FPN: True
ANCHOR_STRIDE: (4, 8, 16, 32, 64)
PRE_NMS_TOP_N_TRAIN: 2000
PRE_NMS_TOP_N_TEST: 1000
POST_NMS_TOP_N_TEST: 1000
FPN_POST_NMS_TOP_N_TEST: 1000
SEG:
USE_FPN: True
USE_FUSE_FEATURE: True
TOP_N_TRAIN: 1000
TOP_N_TEST: 1000
BINARY_THRESH: 0.1
BOX_THRESH: 0.1
MIN_SIZE: 5
SHRINK_RATIO: 0.4
EXPAND_RATIO: 3.0
ROI_HEADS:
USE_FPN: True
BATCH_SIZE_PER_IMAGE: 512
ROI_BOX_HEAD:
POOLER_RESOLUTION: 7
POOLER_SCALES: (0.25,)
POOLER_SAMPLING_RATIO: 2
FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor"
PREDICTOR: "FPNPredictor"
NUM_CLASSES: 2
USE_MASKED_FEATURE: True
ROI_MASK_HEAD:
POOLER_SCALES: (0.25,)
FEATURE_EXTRACTOR: "MaskRCNNFPNFeatureExtractor"
PREDICTOR: "SeqCharMaskRCNNC4Predictor"
POOLER_RESOLUTION: 14
POOLER_RESOLUTION_H: 32
POOLER_RESOLUTION_W: 32
POOLER_SAMPLING_RATIO: 2
RESOLUTION: 28
RESOLUTION_H: 64
RESOLUTION_W: 64
SHARE_BOX_FEATURE_EXTRACTOR: False
CHAR_NUM_CLASSES: 37
USE_WEIGHTED_CHAR_MASK: True
MASK_BATCH_SIZE_PER_IM: 64
USE_MASKED_FEATURE: True
MASK_ON: True
CHAR_MASK_ON: True
SEG_ON: True
# TRAIN_DETECTION_ONLY: True
SEQUENCE:
SEQ_ON: True
NUM_CHAR: 38
BOS_TOKEN: 0
MAX_LENGTH: 32
TEACHER_FORCE_RATIO: 1.0
DATASETS:
# TRAIN: ("synthtext_train",)
TRAIN: ("synthtext_train","icdar_2013_train","icdar_2015_train","scut-eng-char_train","total_text_train")
RATIOS: [0.25,0.25,0.25,0.125,0.125]
# TEST: ("icdar_2015_test",)
TEST: ("total_text_test",)
# TEST: ("rotated_ic13_test_45",)
AUG: True
IGNORE_DIFFICULT: True
MAX_ROTATE_THETA: 90
DATALOADER:
SIZE_DIVISIBILITY: 32
NUM_WORKERS: 4
ASPECT_RATIO_GROUPING: False
SOLVER:
BASE_LR: 0.002 #0.02
WARMUP_FACTOR: 0.1
WEIGHT_DECAY: 0.0001
STEPS: (100000, 160000)
MAX_ITER: 300000
IMS_PER_BATCH: 8
RESUME: False
DISPLAY_FREQ: 20
OUTPUT_DIR: "./output/mixtrain"
TEST:
VIS: True
CHAR_THRESH: 192
IMS_PER_BATCH: 1
INPUT:
MIN_SIZE_TRAIN: (800, 1000, 1200, 1400)
MAX_SIZE_TRAIN: 2333
MIN_SIZE_TEST: 1000
# MIN_SIZE_TEST: 1440
MAX_SIZE_TEST: 4000