Function of infer_img and infer_mode in finetuning

[l03126]

What are these parameters for?

Link : https://github.com/PaddlePaddle/PaddleOCR/blob/main/configs/rec/PP-OCRv4/en_PP-OCRv4_rec.yml

Global:
debug: false
use_gpu: true
epoch_num: 50
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_ppocr_v4
save_epoch_step: 10
eval_batch_step:

• 0
• 2000
  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: ppocr/utils/en_dict.txt
  max_text_length: 25
  infer_mode: false
  use_space_char: true
  distributed: true
  save_res_path: ./output/rec/predicts_ppocrv3.txt
  Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
  name: Cosine
  learning_rate: 0.0005
  warmup_epoch: 5
  regularizer:
  name: L2
  factor: 3.0e-05
  Architecture:
  model_type: rec
  algorithm: SVTR_LCNet
  Transform: null
  Backbone:
  name: PPLCNetV3
  scale: 0.95
  Head:
  name: MultiHead
  head_list:
  • CTCHead:
    Neck:
    name: svtr
    dims: 120
    depth: 2
    hidden_dims: 120
    kernel_size:
    - 1
    - 3
    use_guide: true
    Head:
    fc_decay: 1.0e-05
  • NRTRHead:
    nrtr_dim: 384
    max_text_length: 25
    Loss:
    name: MultiLoss
    loss_config_list:
• CTCLoss: null
• NRTRLoss: null
  PostProcess:
  name: CTCLabelDecode
  Metric:
  name: RecMetric
  main_indicator: acc
  ignore_space: false
  Train:
  dataset:
  name: MultiScaleDataSet
  ds_width: false
  data_dir: ./train_data/
  ext_op_transform_idx: 1
  label_file_list:
  • ./train_data/train_list.txt
    transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • RecConAug:
    prob: 0.5
    ext_data_num: 2
    image_shape:
    • 48
    • 320
    • 3
      max_text_length: 25
  • RecAug: null
  • MultiLabelEncode:
    gtc_encode: NRTRLabelEncode
  • KeepKeys:
    keep_keys:
    • image
    • label_ctc
    • label_gtc
    • length
    • valid_ratio
      sampler:
      name: MultiScaleSampler
      scales:
  • • 320
    • 32
  • • 320
    • 48
  • • 320
    • 64
      first_bs: 96
      fix_bs: false
      divided_factor:
  • 8
  • 16
    is_training: true
    loader:
    shuffle: true
    batch_size_per_card: 96
    drop_last: true
    num_workers: 8
    Eval:
    dataset:
    name: SimpleDataSet
    data_dir: ./train_data
    label_file_list:
  • ./train_data/val_list.txt
    transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • MultiLabelEncode:
    gtc_encode: NRTRLabelEncode
  • RecResizeImg:
    image_shape:
    • 3
    • 48
    • 320
  • KeepKeys:
    keep_keys:
    • image
    • label_ctc
    • label_gtc
    • length
    • valid_ratio
      loader:
      shuffle: false
      drop_last: false
      batch_size_per_card: 128
      num_workers: 4
      profiler_options: null

[GreatV]

The parameters infer_img and infer_mode in the configuration file of PaddleOCR serve the following purposes:

1. infer_img:

   • This parameter specifies the path to an image that will be used for inference.
   • In the provided config file, it is set to "doc/imgs_words/ch/word_1.jpg", meaning that this image will be used when running inference.
   • This parameter is useful when testing a trained model by providing a single image for recognition.

2. infer_mode:

   • This parameter determines whether the model should run in inference mode.
   • When infer_mode: true, the model will not perform training but will instead be used for inference on input images.
   • When infer_mode: false, the model will be used for training or evaluation depending on the context.
   • This is useful when switching between training and inference modes without modifying the script.

Usage in Fine-tuning:

• During fine-tuning, infer_mode should be false so that the model can continue training on new data.
• After fine-tuning, you can set infer_mode to true and specify an image using infer_img to test the trained model.

These parameters are mainly useful for debugging and testing the model after training.

---

Response generated by feifei-bot | chatgpt-4o-latest