Repeating characters in a word are being suppressed by paddleOCR model

[raushani2v]

Hi,

I have trained a custom paddleocr model for character recognition. The repeating characters in a word are being suppressed by the model. for e.g, 40799932 is predicted as 4079932.

What is the reason for this problem? Is there any solution?

I am using following configuration:

Global:
debug: false
use_gpu: true
epoch_num: 5000
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/v3_en_mobile
save_epoch_step: 500
eval_batch_step:

• 0
• 20
  cal_metric_during_train: true
  pretrained_model: null
  checkpoints: null
  save_inference_dir: null
  use_visualdl: false
  infer_img: doc/imgs_words/ch/word_1.jpg
  character_dict_path: ../dataset/wagon/training_data_05-09-2023/char_dict.txt
  max_text_length: 25
  infer_mode: false
  use_space_char: true
  distributed: true
  save_res_path: ./output/rec/predicts_ppocrv3_en.txt
  Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
  name: Cosine
  learning_rate: 0.001
  warmup_epoch: 5
  regularizer:
  name: L2
  factor: 3.0e-05
  Architecture:
  model_type: rec
  algorithm: SVTR_LCNet
  Transform: null
  Backbone:
  name: MobileNetV1Enhance
  scale: 0.5
  last_conv_stride:
  • 1
  • 2
    last_pool_type: avg
    last_pool_kernel_size:
  • 2
  • 2
    Head:
    name: MultiHead
    head_list:
  • CTCHead:
    Neck:
    name: svtr
    dims: 64
    depth: 2
    hidden_dims: 120
    use_guide: true
    Head:
    fc_decay: 1.0e-05
  • SARHead:
    enc_dim: 512
    max_text_length: 25
    Loss:
    name: MultiLoss
    loss_config_list:
• CTCLoss: null
• SARLoss: null
  PostProcess:
  name: CTCLabelDecode
  Metric:
  name: RecMetric
  main_indicator: acc
  ignore_space: false
  Train:
  dataset:
  name: SimpleDataSet
  data_dir: ../dataset/wagon/training_data_05-09-2023
  ext_op_transform_idx: 1
  label_file_list:
  • ../dataset/wagon/training_data_05-09-2023/train.txt
    transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • RecConAug:
    prob: 0.5
    ext_data_num: 2
    image_shape:
    • 32
    • 100
    • 3
      max_text_length: 25
  • RecAug: null
  • MultiLabelEncode: null
  • RecResizeImg:
    image_shape:
    • 3
    • 32
    • 100
  • KeepKeys:
    keep_keys:
    • image
    • label_ctc
    • label_sar
    • length
    • valid_ratio
      loader:
      shuffle: true
      batch_size_per_card: 128
      drop_last: true
      num_workers: 4
      Eval:
      dataset:
      name: SimpleDataSet
      data_dir: ../dataset/wagon/training_data_05-09-2023
      label_file_list:
  • ../dataset/wagon/training_data_05-09-2023/test.txt
    transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • MultiLabelEncode: null
  • RecResizeImg:
    image_shape:
    • 3
    • 32
    • 100
  • KeepKeys:
    keep_keys:
    • image
    • label_ctc
    • label_sar
    • length
    • valid_ratio
      loader:
      shuffle: false
      drop_last: false
      batch_size_per_card: 128
      num_workers: 4
      profiler_options: null