训练paddleOCR文字方向模型的时候发生错误，如何解决？

Question

问题遇到的现象和发生背景

训练paddleOCR文字方向模型的时候发生错误
数据格式是正确的，在同事电脑上已经跑过，在我电脑上就不行

操作环境、软件版本等信息

window10
Python 3.8.19

尝试过的解决方法

百度 Google gpt都无解

我想要达到的结果

想正常跑通代码
这是我的配置文件：

Global:
  use_gpu: True
  epoch_num: 100
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: ./output/cls/mv3/
  save_epoch_step: 3
  # evaluation is run every 5000 iterations after the 4000th iteration
  eval_batch_step: [0, 1000]
  cal_metric_during_train: True
  pretrained_model:
  checkpoints:
  save_inference_dir:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  label_list: ['0','180']

Architecture:
  model_type: cls
  algorithm: CLS
  Transform:
  Backbone:
    name: MobileNetV3
    scale: 0.35
    model_name: small
  Neck:
  Head:
    name: ClsHead
    class_dim: 2

Loss:
  name: ClsLoss

Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
    name: Cosine
    learning_rate: 0.001
  regularizer:
    name: 'L2'
    factor: 0

PostProcess:
  name: ClsPostProcess

Metric:
  name: ClsMetric
  main_indicator: acc

Train:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/cls/train
    label_file_list:
      - ./train_data/cls/cls_gt_train.txt
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - ClsLabelEncode: # Class handling label
      - BaseDataAugmentation:
      - RandAugment:
      - ClsResizeImg:
          image_shape: [3, 30, 300]
      - KeepKeys:
          keep_keys: ['image', 'label'] # dataloader will return list in this order
  loader:
    shuffle: True
    batch_size_per_card: 1
    drop_last: True
    num_workers: 0

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/cls/train
    label_file_list:
      - ./train_data/cls/cls_gt_train.txt
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - ClsLabelEncode: # Class handling label
      - ClsResizeImg:
          image_shape: [3, 30, 300]
      - KeepKeys:
          keep_keys: ['image', 'label'] # dataloader will return list in this order
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 1
    num_workers: 0

##这是我的报错信息

(paddleOCR) D:\PaddleOCR-release-2.7.1>python tools/train.py -c configs/cls/cls_mv3.yml
[2024/08/12 13:26:44] ppocr INFO: Architecture :
[2024/08/12 13:26:44] ppocr INFO:     Backbone :
[2024/08/12 13:26:44] ppocr INFO:         model_name : small
[2024/08/12 13:26:44] ppocr INFO:         name : MobileNetV3
[2024/08/12 13:26:44] ppocr INFO:         scale : 0.35
[2024/08/12 13:26:44] ppocr INFO:     Head :
[2024/08/12 13:26:44] ppocr INFO:         class_dim : 2
[2024/08/12 13:26:44] ppocr INFO:         name : ClsHead
[2024/08/12 13:26:44] ppocr INFO:     Neck : None
[2024/08/12 13:26:44] ppocr INFO:     Transform : None
[2024/08/12 13:26:44] ppocr INFO:     algorithm : CLS
[2024/08/12 13:26:44] ppocr INFO:     model_type : cls
[2024/08/12 13:26:44] ppocr INFO: Eval :
[2024/08/12 13:26:44] ppocr INFO:     dataset :
[2024/08/12 13:26:44] ppocr INFO:         data_dir : ./train_data/cls/train
[2024/08/12 13:26:44] ppocr INFO:         label_file_list : ['./train_data/cls/cls_gt_train.txt']
[2024/08/12 13:26:44] ppocr INFO:         name : SimpleDataSet
[2024/08/12 13:26:44] ppocr INFO:         transforms :
[2024/08/12 13:26:44] ppocr INFO:             DecodeImage :
[2024/08/12 13:26:44] ppocr INFO:                 channel_first : False
[2024/08/12 13:26:44] ppocr INFO:                 img_mode : BGR
[2024/08/12 13:26:44] ppocr INFO:             ClsLabelEncode : None
[2024/08/12 13:26:44] ppocr INFO:             ClsResizeImg :
[2024/08/12 13:26:44] ppocr INFO:                 image_shape : [3, 30, 300]
[2024/08/12 13:26:44] ppocr INFO:             KeepKeys :
[2024/08/12 13:26:44] ppocr INFO:                 keep_keys : ['image', 'label']
[2024/08/12 13:26:44] ppocr INFO:     loader :
[2024/08/12 13:26:44] ppocr INFO:         batch_size_per_card : 1
[2024/08/12 13:26:44] ppocr INFO:         drop_last : False
[2024/08/12 13:26:44] ppocr INFO:         num_workers : 0
[2024/08/12 13:26:44] ppocr INFO:         shuffle : False
[2024/08/12 13:26:44] ppocr INFO: Global :
[2024/08/12 13:26:44] ppocr INFO:     cal_metric_during_train : True
[2024/08/12 13:26:44] ppocr INFO:     checkpoints : None
[2024/08/12 13:26:44] ppocr INFO:     distributed : False
[2024/08/12 13:26:44] ppocr INFO:     epoch_num : 100
[2024/08/12 13:26:44] ppocr INFO:     eval_batch_step : [0, 1000]
[2024/08/12 13:26:44] ppocr INFO:     infer_img : doc/imgs_words_en/word_10.png
[2024/08/12 13:26:44] ppocr INFO:     label_list : ['0', '180']
[2024/08/12 13:26:44] ppocr INFO:     log_smooth_window : 20
[2024/08/12 13:26:44] ppocr INFO:     pretrained_model : None
[2024/08/12 13:26:44] ppocr INFO:     print_batch_step : 10
[2024/08/12 13:26:44] ppocr INFO:     save_epoch_step : 3
[2024/08/12 13:26:44] ppocr INFO:     save_inference_dir : None
[2024/08/12 13:26:44] ppocr INFO:     save_model_dir : ./output/cls/mv3/
[2024/08/12 13:26:44] ppocr INFO:     use_gpu : True
[2024/08/12 13:26:44] ppocr INFO:     use_visualdl : False
[2024/08/12 13:26:44] ppocr INFO: Loss :
[2024/08/12 13:26:44] ppocr INFO:     name : ClsLoss
[2024/08/12 13:26:44] ppocr INFO: Metric :
[2024/08/12 13:26:44] ppocr INFO:     main_indicator : acc
[2024/08/12 13:26:44] ppocr INFO:     name : ClsMetric
[2024/08/12 13:26:44] ppocr INFO: Optimizer :
[2024/08/12 13:26:44] ppocr INFO:     beta1 : 0.9
[2024/08/12 13:26:44] ppocr INFO:     beta2 : 0.999
[2024/08/12 13:26:44] ppocr INFO:     lr :
[2024/08/12 13:26:44] ppocr INFO:         learning_rate : 0.001
[2024/08/12 13:26:44] ppocr INFO:         name : Cosine
[2024/08/12 13:26:44] ppocr INFO:     name : Adam
[2024/08/12 13:26:44] ppocr INFO:     regularizer :
[2024/08/12 13:26:44] ppocr INFO:         factor : 0
[2024/08/12 13:26:44] ppocr INFO:         name : L2
[2024/08/12 13:26:44] ppocr INFO: PostProcess :
[2024/08/12 13:26:44] ppocr INFO:     name : ClsPostProcess
[2024/08/12 13:26:44] ppocr INFO: Train :
[2024/08/12 13:26:44] ppocr INFO:     dataset :
[2024/08/12 13:26:44] ppocr INFO:         data_dir : ./train_data/cls/train
[2024/08/12 13:26:44] ppocr INFO:         label_file_list : ['./train_data/cls/cls_gt_train.txt']
[2024/08/12 13:26:44] ppocr INFO:         name : SimpleDataSet
[2024/08/12 13:26:44] ppocr INFO:         transforms :
[2024/08/12 13:26:44] ppocr INFO:             DecodeImage :
[2024/08/12 13:26:44] ppocr INFO:                 channel_first : False
[2024/08/12 13:26:44] ppocr INFO:                 img_mode : BGR
[2024/08/12 13:26:44] ppocr INFO:             ClsLabelEncode : None
[2024/08/12 13:26:44] ppocr INFO:             BaseDataAugmentation : None
[2024/08/12 13:26:44] ppocr INFO:             RandAugment : None
[2024/08/12 13:26:44] ppocr INFO:             ClsResizeImg :
[2024/08/12 13:26:44] ppocr INFO:                 image_shape : [3, 30, 300]
[2024/08/12 13:26:44] ppocr INFO:             KeepKeys :
[2024/08/12 13:26:44] ppocr INFO:                 keep_keys : ['image', 'label']
[2024/08/12 13:26:44] ppocr INFO:     loader :
[2024/08/12 13:26:44] ppocr INFO:         batch_size_per_card : 1
[2024/08/12 13:26:44] ppocr INFO:         drop_last : True
[2024/08/12 13:26:44] ppocr INFO:         num_workers : 0
[2024/08/12 13:26:44] ppocr INFO:         shuffle : True
[2024/08/12 13:26:44] ppocr INFO: profiler_options : None
[2024/08/12 13:26:44] ppocr INFO: train with paddle 2.6.1 and device Place(gpu:0)
[2024/08/12 13:26:44] ppocr INFO: Initialize indexs of datasets:['./train_data/cls/cls_gt_train.txt']
list index out of range
[2024/08/12 13:26:44] ppocr INFO: Initialize indexs of datasets:['./train_data/cls/cls_gt_train.txt']
W0812 13:26:44.671368   520 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.6, Runtime API Version: 11.7
W0812 13:26:44.674342   520 gpu_resources.cc:164] device: 0, cuDNN Version: 8.9.
[2024/08/12 13:26:45] ppocr INFO: train dataloader has 12362 iters
[2024/08/12 13:26:45] ppocr INFO: valid dataloader has 12362 iters
[2024/08/12 13:26:45] ppocr INFO: train from scratch
[2024/08/12 13:26:45] ppocr INFO: During the training process, after the 0th iteration, an evaluation is run every 1000 iterations
[2024/08/12 13:26:46] ppocr ERROR: When parsing line cam#0-NG(OCR)-20240629-195141-478_crop_0.png       0
, error happened with msg: Traceback (most recent call last):
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 157, in __getitem__
    data['image'] = img
RecursionError: maximum recursion depth exceeded while calling a Python object

Fatal Python error: Cannot recover from stack overflow.
Python runtime state: initialized

Current thread 0x000012b4 (most recent call first):
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 157 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  File "D:\PaddleOCR-release-2.7.1\ppocr\data\simple_dataset.py", line 169 in __getitem__
  ...

Thread 0x00000208 (most recent call first):
  File "D:\ProgramData\anaconda3\envs\paddleOCR\lib\site-packages\paddle\io\dataloader\dataloader_iter.py", line 291 in __next__
  File "D:\PaddleOCR-release-2.7.1\tools\program.py", line 272 in train
  File "tools/train.py", line 200 in main
  File "tools/train.py", line 229 in <module>

Answer 1

下午好🌅🌅🌅
本答案参考ChatGPT-3.5

训练过程中出现错误的原因可能是由于模型没有正确初始化，也可能是数据格式不正确。为了解决这个问题，你可以尝试以下几种解决方法：

1. 检查你的模型和数据加载器是否正确。确保它们的名称和路径与示例中的内容匹配。

model_path = "./output/cls/mv3/"

models目录下应该有包含这个路径的文件，如MobileNetV3.h5或small.h5。检查数据集和标签文件的路径是否正确，并确认它们的内容符合预期。

1. 确保你的labels.txt文件中包含了所有的类标签（0到180）。

2. 在你的代码中使用decode_image函数来加载图像。例如：

img = decode_image(img_path)

确保你在调用decode_image函数之前已经加载了对应的图片文件。

1. 使用base_data_augmentation模块来处理数据。例如：

data augumentation = base_data_augmentation()

# ...
augmented_data = augumentation(data)

# ...

注意，你需要将base_data_augmentation()函数替换为你自己的数据预处理函数。

1. 使用resize_img模块对图像进行缩放。例如：

resize_img(img_path, new_shape=(30, 300))

请将new_shape参数设置为(30, 300)。

1. 使用keep_keys参数指定decode_image函数返回的数据中的保留键。例如：

keep_keys = ['image', 'label']
decoded_data = decode_image(img_path, keep_keys=keep_keys)

在训练模型时，你需要使用这些数据，而不是原始数据。

1. 如果上述方法都不能解决问题，那么你可能需要进一步调试你的代码，看看是否有其他变量的影响。或者，如果你使用的是paddleOCR库，你可能需要查看相关文档以获取更多的帮助。

希望这些建议能对你有所帮助！如果还有任何疑问，欢迎随时向我提问。