TypeError: batch data con only contains: tensor, numpy.ndarray, dict, list, number, but got <class 'numpy.bool_'>

[yusufelgen07]

when i try to fine tune a model for testing i got an error saying

[2024/06/25 11:49:02] ppocr ERROR: When parsing line icdar_c4_train_imgs/img_955.jpg [{"transcription": "rage", "points": [[5, 70], [148, 56], [149, 98], [5, 112]]}, {"transcription": "###", "points": [[477, 168], [505, 165], [512, 195], [484, 198]]}, {"transcription": "###", "points": [[350, 183], [384, 175], [386, 197], [352, 204]]}, {"transcription": "###", "points": [[304, 212], [340, 207], [342, 226], [306, 232]]}, {"transcription": "###", "points": [[340, 206], [393, 197], [396, 218], [344, 226]]}, {"transcription": "###", "points": [[304, 191], [345, 184], [348, 203], [307, 210]]}, {"transcription": "###", "points": [[416, 178], [442, 175], [447, 207], [421, 210]]}, {"transcription": "###", "points": [[368, 267], [383, 261], [396, 292], [381, 298]]}, {"transcription": "###", "points": [[357, 271], [367, 267], [376, 288], [366, 293]]}, {"transcription": "###", "points": [[382, 258], [402, 250], [410, 272], [391, 280]]}, {"transcription": "SALE", "points": [[534, 121], [590, 108], [598, 149], [542, 162]]}, {"transcription": "50%", "points": [[535, 195], [592, 191], [599, 239], [542, 242]]}, {"transcription": "FREE", "points": [[809, 103], [841, 97], [842, 109], [810, 116]]}]
, error happened with msg: Traceback (most recent call last):
File "/kaggle/working/PaddleOCR/ppocr/data/simple_dataset.py", line 162, in getitem
outs = transform(data, self.ops)
File "/kaggle/working/PaddleOCR/ppocr/data/imaug/init.py", line 71, in transform
data = op(data)
File "/kaggle/working/PaddleOCR/ppocr/data/imaug/operators.py", line 131, in call
data_list.append(data[key])
KeyError: 'shape'

then i looked on the internet for similar issue but i didn't find anything so i changed the code myself i added to simple_dataset.py
those two lines
img = cv2.imread(data["img_path"])
data["shape"] = [img.shape[0],img.shape[1]]
like that

def get_ext_data(self):
ext_data_num = 0
for op in self.ops:
if hasattr(op, "ext_data_num"):
ext_data_num = getattr(op, "ext_data_num")
break
load_data_ops = self.ops[: self.ext_op_transform_idx]
ext_data = []

    while len(ext_data) < ext_data_num:
        file_idx = self.data_idx_order_list[np.random.randint(self.__len__())]
        data_line = self.data_lines[file_idx]
        data_line = data_line.decode("utf-8")
        substr = data_line.strip("\n").split(self.delimiter)
        file_name = substr[0]
        file_name = self._try_parse_filename_list(file_name)
        label = substr[1]
        img_path = os.path.join(self.data_dir, file_name)
        data = {"img_path": img_path, "label": label}
        if not os.path.exists(img_path):
            continue
        with open(data["img_path"], "rb") as f:
            img = f.read()
            data["image"] = img
        data = transform(data, load_data_ops)
        img = cv2.imread(data["img_path"])
        data["shape"] = [img.shape[0],img.shape[1]]
        if data is None:
            continue
        if "polys" in data.keys():
            if data["polys"].shape[1] != 4:
                continue
        ext_data.append(data)
    return ext_data

but i got this error now
Exception in thread Thread-3 (_thread_loop):
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/opt/conda/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/dataloader_iter.py", line 603, in _thread_loop
batch = self._get_data()
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/dataloader_iter.py", line 751, in get_data
batch.reraise()
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/worker.py", line 187, in reraise
raise self.exc_type(msg)
TypeError: DataLoader worker(0) caught TypeError with message:
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/worker.py", line 372, in worker_loop
batch = fetcher.fetch(indices)
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/fetcher.py", line 85, in fetch
data = self.collate_fn(data)
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/collate.py", line 75, in default_collate_fn
return [default_collate_fn(fields) for fields in zip(*batch)]
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/collate.py", line 75, in
return [default_collate_fn(fields) for fields in zip(*batch)]
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/collate.py", line 75, in default_collate_fn
return [default_collate_fn(fields) for fields in zip(*batch)]
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/collate.py", line 75, in
return [default_collate_fn(fields) for fields in zip(*batch)]
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/collate.py", line 77, in default_collate_fn
raise TypeError(
TypeError: batch data con only contains: tensor, numpy.ndarray, dict, list, number, but got <class 'numpy.bool'>
Traceback (most recent call last):
File "/kaggle/working/PaddleOCR/tools/train.py", line 255, in
main(config, device, logger, vdl_writer, seed)
File "/kaggle/working/PaddleOCR/tools/train.py", line 208, in main
program.train(
File "/kaggle/working/PaddleOCR/tools/program.py", line 304, in train
for idx, batch in enumerate(train_dataloader):
File "/opt/conda/lib/python3.10/site-packages/paddle/io/dataloader/dataloader_iter.py", line 825, in next
self.reader.read_next_list()[0]
SystemError: (Fatal) Blocking queue is killed because the data reader raises an exception.
[Hint: Expected killed != true, but received killed:1 == true:1.] (at /paddle/paddle/fluid/operators/reader/blocking_queue.h:175)

my conf file:

Architecture:
Backbone:
model_name: large
name: MobileNetV3
scale: 0.5
Head:
k: 50
name: DBHead
Neck:
name: DBFPN
out_channels: 256
Transform: null
algorithm: DB
model_type: det
Eval:
dataset:
data_dir: /kaggle/working/PaddleOCR/train_data/icdar2015/text_localization
label_file_list:
- /kaggle/working/PaddleOCR/train_data/icdar2015/text_localization/test_icdar2015_label.txt
name: SimpleDataSet
transforms:
- DecodeImage:
channel_first: false
img_mode: BGR
- DetLabelEncode: null
- DetResizeForTest:
image_shape:
- 736
- 1280
- NormalizeImage:
mean:
- 0.485
- 0.456
- 0.406
order: hwc
scale: 1./255.
std:
- 0.229
- 0.224
- 0.225
- ToCHWImage: null
- KeepKeys:
keep_keys:
- image
- shape
- polys
- ignore_tags
loader:
batch_size_per_card: 1
drop_last: false
num_workers: 2
shuffle: false
Global:
cal_metric_during_train: true
checkpoints: null
epoch_num: 5
eval_batch_step:

• 0
• 2000
  infer_img: doc/imgs_en/img_10.jpg
  log_smooth_window: 20
  pretrained_model: /kaggle/working/PaddleOCR/pretrain_models/MobileNetV3_large_x0_5_pretrained
  print_batch_step: 10
  save_epoch_step: 1200
  save_inference_dir: null
  save_model_dir: /kaggle/working/PaddleOCR/output/db_mv3/
  save_res_path: /kaggle/working/PaddleOCR/output/det_db/predicts_db.txt
  use_gpu: true
  use_mlu: false
  use_visualdl: false
  use_xpu: false
  Loss:
  alpha: 5
  balance_loss: true
  beta: 10
  main_loss_type: DiceLoss
  name: DBLoss
  ohem_ratio: 3
  Metric:
  main_indicator: hmean
  name: DetMetric
  Optimizer:
  beta1: 0.9
  beta2: 0.999
  lr:
  learning_rate: 0.001
  name: Adam
  regularizer:
  factor: 0
  name: L2
  PostProcess:
  box_thresh: 0.6
  max_candidates: 1000
  name: DBPostProcess
  thresh: 0.3
  unclip_ratio: 1.5
  Train:
  dataset:
  data_dir: /kaggle/working/PaddleOCR/train_data/icdar2015/text_localization
  label_file_list:
  • /kaggle/working/PaddleOCR/train_data/icdar2015/text_localization/train_icdar2015_label.txt
    name: SimpleDataSet
    ratio_list:
  • 1.0
    transforms:
  • DecodeImage:
    channel_first: false
    img_mode: BGR
  • DetLabelEncode: null
  • IaaAugment:
    augmenter_args:
    • args:
      p: 0.5
      type: Fliplr
    • args:
      rotate:
      • -10
      • 10
        type: Affine
    • args:
      size:
      • 0.5
      • 3
        type: Resize
  • EastRandomCropData:
    keep_ratio: true
    max_tries: 50
    size:
    • 640
    • 640
  • MakeBorderMap:
    shrink_ratio: 0.4
    thresh_max: 0.7
    thresh_min: 0.3
  • MakeShrinkMap:
    min_text_size: 8
    shrink_ratio: 0.4
  • NormalizeImage:
    mean:
    • 0.485
    • 0.456
    • 0.406
      order: hwc
      scale: 1./255.
      std:
    • 0.229
    • 0.224
    • 0.225
  • ToCHWImage: null
  • KeepKeys:
    keep_keys:
    • image
    • shape
    • polys
    • ignore_tags
      loader:
      batch_size_per_card: 1
      drop_last: false
      num_workers: 8
      shuffle: true
      use_shared_memory: true
      wandb:
      project: OCR_with_Paddle

[SWHL]

Guess there was a problem reading a certain image.
Suggest checking if there are any images in the dataset that OpenCV cannot read correctly.