PPOCRLabel标注后的数据导入Vi-Layoutxlm模型进行训练，报错KeyError: 'label'

[Renjunhua30]

(Vi_layoutxlm) wyy@wyy-SYS-7049GP-TRT:~/railway/PaddleOCR$ bash Tra-Rail.sh
LAUNCH INFO 2024-11-06 16:14:41,582 ----------- Configuration ----------------------
LAUNCH INFO 2024-11-06 16:14:41,583 auto_parallel_config: None
LAUNCH INFO 2024-11-06 16:14:41,583 devices: 0,1,2,3
LAUNCH INFO 2024-11-06 16:14:41,583 elastic_level: -1
LAUNCH INFO 2024-11-06 16:14:41,583 elastic_timeout: 30
LAUNCH INFO 2024-11-06 16:14:41,583 gloo_port: 6767
LAUNCH INFO 2024-11-06 16:14:41,583 host: None
LAUNCH INFO 2024-11-06 16:14:41,583 ips: None
LAUNCH INFO 2024-11-06 16:14:41,583 job_id: default
LAUNCH INFO 2024-11-06 16:14:41,583 legacy: False
LAUNCH INFO 2024-11-06 16:14:41,583 log_dir: log
LAUNCH INFO 2024-11-06 16:14:41,583 log_level: INFO
LAUNCH INFO 2024-11-06 16:14:41,583 log_overwrite: False
LAUNCH INFO 2024-11-06 16:14:41,583 master: None
LAUNCH INFO 2024-11-06 16:14:41,583 max_restart: 3
LAUNCH INFO 2024-11-06 16:14:41,583 nnodes: 1
LAUNCH INFO 2024-11-06 16:14:41,583 nproc_per_node: None
LAUNCH INFO 2024-11-06 16:14:41,583 rank: -1
LAUNCH INFO 2024-11-06 16:14:41,583 run_mode: collective
LAUNCH INFO 2024-11-06 16:14:41,583 server_num: None
LAUNCH INFO 2024-11-06 16:14:41,583 servers:
LAUNCH INFO 2024-11-06 16:14:41,583 start_port: 6070
LAUNCH INFO 2024-11-06 16:14:41,583 trainer_num: None
LAUNCH INFO 2024-11-06 16:14:41,583 trainers:
LAUNCH INFO 2024-11-06 16:14:41,583 training_script: tools/train.py
LAUNCH INFO 2024-11-06 16:14:41,583 training_script_args: ['-c', 'configs/kie/vi_layoutxlm/ser_vi_layoutxlm_TR.yml']
LAUNCH INFO 2024-11-06 16:14:41,583 with_gloo: 1
LAUNCH INFO 2024-11-06 16:14:41,583 --------------------------------------------------
LAUNCH INFO 2024-11-06 16:14:41,584 Job: default, mode collective, replicas 1[1:1], elastic False
LAUNCH INFO 2024-11-06 16:14:41,592 Run Pod: cmfmde, replicas 4, status ready
LAUNCH INFO 2024-11-06 16:14:41,687 Watching Pod: cmfmde, replicas 4, status running
[2024/11/06 16:14:49] ppocr INFO: Architecture :
[2024/11/06 16:14:49] ppocr INFO: Backbone :
[2024/11/06 16:14:49] ppocr INFO: checkpoints : None
[2024/11/06 16:14:49] ppocr INFO: mode : vi
[2024/11/06 16:14:49] ppocr INFO: name : LayoutXLMForSer
[2024/11/06 16:14:49] ppocr INFO: num_classes : 7
[2024/11/06 16:14:49] ppocr INFO: pretrained : True
[2024/11/06 16:14:49] ppocr INFO: Transform : None
[2024/11/06 16:14:49] ppocr INFO: algorithm : LayoutXLM
[2024/11/06 16:14:49] ppocr INFO: model_type : kie
[2024/11/06 16:14:49] ppocr INFO: Eval :
[2024/11/06 16:14:49] ppocr INFO: dataset :
[2024/11/06 16:14:49] ppocr INFO: data_dir : ./train_data/TR4/det/val
[2024/11/06 16:14:49] ppocr INFO: label_file_list : ['./train_data/TR4/det/val.json']
[2024/11/06 16:14:49] ppocr INFO: name : SimpleDataSet
[2024/11/06 16:14:49] ppocr INFO: transforms :
[2024/11/06 16:14:49] ppocr INFO: DecodeImage :
[2024/11/06 16:14:49] ppocr INFO: channel_first : False
[2024/11/06 16:14:49] ppocr INFO: img_mode : RGB
[2024/11/06 16:14:49] ppocr INFO: VQATokenLabelEncode :
[2024/11/06 16:14:49] ppocr INFO: algorithm : LayoutXLM
[2024/11/06 16:14:49] ppocr INFO: class_path : ./train_data/TR4/TR4_label.txt
[2024/11/06 16:14:49] ppocr INFO: contains_re : False
[2024/11/06 16:14:49] ppocr INFO: order_method : tb-yx
[2024/11/06 16:14:49] ppocr INFO: use_textline_bbox_info : True
[2024/11/06 16:14:49] ppocr INFO: VQATokenPad :
[2024/11/06 16:14:49] ppocr INFO: max_seq_len : 512
[2024/11/06 16:14:49] ppocr INFO: return_attention_mask : True
[2024/11/06 16:14:49] ppocr INFO: VQASerTokenChunk :
[2024/11/06 16:14:49] ppocr INFO: max_seq_len : 512
[2024/11/06 16:14:49] ppocr INFO: Resize :
[2024/11/06 16:14:49] ppocr INFO: size : [224, 224]
[2024/11/06 16:14:49] ppocr INFO: NormalizeImage :
[2024/11/06 16:14:49] ppocr INFO: mean : [123.675, 116.28, 103.53]
[2024/11/06 16:14:49] ppocr INFO: order : hwc
[2024/11/06 16:14:49] ppocr INFO: scale : 1
[2024/11/06 16:14:49] ppocr INFO: std : [58.395, 57.12, 57.375]
[2024/11/06 16:14:49] ppocr INFO: ToCHWImage : None
[2024/11/06 16:14:49] ppocr INFO: KeepKeys :
[2024/11/06 16:14:49] ppocr INFO: keep_keys : ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels']
[2024/11/06 16:14:49] ppocr INFO: loader :
[2024/11/06 16:14:49] ppocr INFO: batch_size_per_card : 1
[2024/11/06 16:14:49] ppocr INFO: drop_last : False
[2024/11/06 16:14:49] ppocr INFO: num_workers : 4
[2024/11/06 16:14:49] ppocr INFO: shuffle : False
[2024/11/06 16:14:49] ppocr INFO: Global :
[2024/11/06 16:14:49] ppocr INFO: amp_custom_white_list : ['scale', 'concat', 'elementwise_add']
[2024/11/06 16:14:49] ppocr INFO: cal_metric_during_train : False
[2024/11/06 16:14:49] ppocr INFO: distributed : True
[2024/11/06 16:14:49] ppocr INFO: epoch_num : 10
[2024/11/06 16:14:49] ppocr INFO: eval_batch_step : [0, 10]
[2024/11/06 16:14:49] ppocr INFO: infer_img : ./train_data/TR4/det/val/val.json
[2024/11/06 16:14:49] ppocr INFO: infer_mode : False
[2024/11/06 16:14:49] ppocr INFO: kie_det_model_dir : None
[2024/11/06 16:14:49] ppocr INFO: kie_rec_model_dir : None
[2024/11/06 16:14:49] ppocr INFO: log_smooth_window : 10
[2024/11/06 16:14:49] ppocr INFO: print_batch_step : 10
[2024/11/06 16:14:49] ppocr INFO: save_epoch_step : 2000
[2024/11/06 16:14:49] ppocr INFO: save_inference_dir : None
[2024/11/06 16:14:49] ppocr INFO: save_model_dir : ./output/TR_vi_layoutxlm
[2024/11/06 16:14:49] ppocr INFO: save_res_path : ./output/ser/TR4/res
[2024/11/06 16:14:49] ppocr INFO: seed : 2022
[2024/11/06 16:14:49] ppocr INFO: use_gpu : True
[2024/11/06 16:14:49] ppocr INFO: use_visualdl : False
[2024/11/06 16:14:49] ppocr INFO: Loss :
[2024/11/06 16:14:49] ppocr INFO: key : backbone_out
[2024/11/06 16:14:49] ppocr INFO: name : VQASerTokenLayoutLMLoss
[2024/11/06 16:14:49] ppocr INFO: num_classes : 7
[2024/11/06 16:14:49] ppocr INFO: Metric :
[2024/11/06 16:14:49] ppocr INFO: main_indicator : hmean
[2024/11/06 16:14:49] ppocr INFO: name : VQASerTokenMetric
[2024/11/06 16:14:49] ppocr INFO: Optimizer :
[2024/11/06 16:14:49] ppocr INFO: beta1 : 0.9
[2024/11/06 16:14:49] ppocr INFO: beta2 : 0.999
[2024/11/06 16:14:49] ppocr INFO: lr :
[2024/11/06 16:14:49] ppocr INFO: epochs : 10
[2024/11/06 16:14:49] ppocr INFO: learning_rate : 5e-05
[2024/11/06 16:14:49] ppocr INFO: name : Linear
[2024/11/06 16:14:49] ppocr INFO: warmup_epoch : 2
[2024/11/06 16:14:49] ppocr INFO: name : AdamW
[2024/11/06 16:14:49] ppocr INFO: regularizer :
[2024/11/06 16:14:49] ppocr INFO: factor : 0.0
[2024/11/06 16:14:49] ppocr INFO: name : L2
[2024/11/06 16:14:49] ppocr INFO: PostProcess :
[2024/11/06 16:14:49] ppocr INFO: class_path : ./train_data/TR4/TR4_label.txt
[2024/11/06 16:14:49] ppocr INFO: name : VQASerTokenLayoutLMPostProcess
[2024/11/06 16:14:49] ppocr INFO: Train :
[2024/11/06 16:14:49] ppocr INFO: dataset :
[2024/11/06 16:14:49] ppocr INFO: data_dir : ./train_data/TR4/det/train
[2024/11/06 16:14:49] ppocr INFO: label_file_list : ['./train_data/TR4/det/train.json']
[2024/11/06 16:14:49] ppocr INFO: name : SimpleDataSet
[2024/11/06 16:14:49] ppocr INFO: ratio_list : [1.0]
[2024/11/06 16:14:49] ppocr INFO: transforms :
[2024/11/06 16:14:49] ppocr INFO: DecodeImage :
[2024/11/06 16:14:49] ppocr INFO: channel_first : False
[2024/11/06 16:14:49] ppocr INFO: img_mode : RGB
[2024/11/06 16:14:49] ppocr INFO: VQATokenLabelEncode :
[2024/11/06 16:14:49] ppocr INFO: algorithm : LayoutXLM
[2024/11/06 16:14:49] ppocr INFO: class_path : ./train_data/TR4/TR4_label.txt
[2024/11/06 16:14:49] ppocr INFO: contains_re : False
[2024/11/06 16:14:49] ppocr INFO: order_method : tb-yx
[2024/11/06 16:14:49] ppocr INFO: use_textline_bbox_info : True
[2024/11/06 16:14:49] ppocr INFO: VQATokenPad :
[2024/11/06 16:14:49] ppocr INFO: max_seq_len : 512
[2024/11/06 16:14:49] ppocr INFO: return_attention_mask : True
[2024/11/06 16:14:49] ppocr INFO: VQASerTokenChunk :
[2024/11/06 16:14:49] ppocr INFO: max_seq_len : 512
[2024/11/06 16:14:49] ppocr INFO: Resize :
[2024/11/06 16:14:49] ppocr INFO: size : [224, 224]
[2024/11/06 16:14:49] ppocr INFO: NormalizeImage :
[2024/11/06 16:14:49] ppocr INFO: mean : [123.675, 116.28, 103.53]
[2024/11/06 16:14:49] ppocr INFO: order : hwc
[2024/11/06 16:14:49] ppocr INFO: scale : 1
[2024/11/06 16:14:49] ppocr INFO: std : [58.395, 57.12, 57.375]
[2024/11/06 16:14:49] ppocr INFO: ToCHWImage : None
[2024/11/06 16:14:49] ppocr INFO: KeepKeys :
[2024/11/06 16:14:49] ppocr INFO: keep_keys : ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels']
[2024/11/06 16:14:49] ppocr INFO: loader :
[2024/11/06 16:14:49] ppocr INFO: batch_size_per_card : 1
[2024/11/06 16:14:49] ppocr INFO: drop_last : False
[2024/11/06 16:14:49] ppocr INFO: num_workers : 4
[2024/11/06 16:14:49] ppocr INFO: shuffle : True
[2024/11/06 16:14:49] ppocr INFO: profiler_options : None
[2024/11/06 16:14:49] ppocr INFO: train with paddle 2.5.2 and device Place(gpu:0)
======================= Modified FLAGS detected =======================
FLAGS(name='FLAGS_selected_gpus', current_value='0', default_value='')

I1106 16:14:49.584448 280711 tcp_utils.cc:181] The server starts to listen on IP_ANY:54990
I1106 16:14:49.584709 280711 tcp_utils.cc:130] Successfully connected to 127.0.1.1:54990
W1106 16:14:53.078943 280711 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 7.5, Driver API Version: 12.4, Runtime API Version: 12.0
W1106 16:14:53.079993 280711 gpu_resources.cc:149] device: 0, cuDNN Version: 8.9.
[2024/11/06 16:14:53] ppocr INFO: Initialize indexs of datasets:['./train_data/TR4/det/train.json']
[2024-11-06 16:14:55,966] [ INFO] - Already cached /home/wyy/.paddlenlp/models/layoutxlm-base-uncased/sentencepiece.bpe.model
[2024-11-06 16:14:56,645] [ INFO] - tokenizer config file saved in /home/wyy/.paddlenlp/models/layoutxlm-base-uncased/tokenizer_config.json
[2024-11-06 16:14:56,645] [ INFO] - Special tokens file saved in /home/wyy/.paddlenlp/models/layoutxlm-base-uncased/special_tokens_map.json
[2024/11/06 16:14:56] ppocr INFO: Initialize indexs of datasets:['./train_data/TR4/det/val.json']
[2024-11-06 16:14:56,661] [ INFO] - Already cached /home/wyy/.paddlenlp/models/layoutxlm-base-uncased/sentencepiece.bpe.model
[2024-11-06 16:14:57,307] [ INFO] - tokenizer config file saved in /home/wyy/.paddlenlp/models/layoutxlm-base-uncased/tokenizer_config.json
[2024-11-06 16:14:57,307] [ INFO] - Special tokens file saved in /home/wyy/.paddlenlp/models/layoutxlm-base-uncased/special_tokens_map.json
[2024-11-06 16:14:57,330] [ INFO] - Already cached /home/wyy/.paddlenlp/models/vi-layoutxlm-base-uncased/model_state.pdparams
[2024-11-06 16:15:03,543] [ INFO] - Weights of LayoutXLMForTokenClassification not initialized from pretrained model: ['classifier.weight', 'classifier.bias']
[2024/11/06 16:15:06] ppocr INFO: train dataloader has 17 iters
[2024/11/06 16:15:06] ppocr INFO: valid dataloader has 22 iters
[2024/11/06 16:15:06] ppocr INFO: During the training process, after the 0th iteration, an evaluation is run every 10 iterations
[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_04.jpg [{"transcription": "待识别", "points": [[154, 255], [1582, 255], [1582, 54 [154, 541]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[154, 255], [1582, 255], [1582, 541], [154, 541]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_7.jpg [{"transcription": "待识别", "points": [[167, 260], [1523, 260], [1523, 11, [167, 1116]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[167, 260], [1523, 260], [1523, 1116], [167, 1116]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_10.jpg [{"transcription": "A", "points": [[176, 130], [1476, 130], [1476, 2060], [176, 2060]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_08.jpg [{"transcription": "待识别", "points": [[182, 269], [1504, 269], [4, 2074], [182, 2074]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_8.jpg [{"transcription": "中国铁路信息科技集团有限公司办公室", "points": [[118, [444, 911], [118, 911]], "difficult": false, "key_cls": "发布部门"}, {"transcription": "2023年8月31日", "points": [[481, 882], [639, 882], [639, 909], [481, 909]], "difficult": false, "key_cls": "发布时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《中国国家铁路集团有限公司信息技术中心评审专家遴选办法》的通知(信技网技〔2023〕6号)_页面_4.jpg [{"transcription": "店", "points": [[178, 266], [1464, 266], [1464, 2074], [178, 2074]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_13.jpg [{"transcription": "商", "points": [[171, 249], [1490, 249], [1490 2021], [171, 2021]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团网信专家库管理工作细则_页面_05.jpg [{"transcription": "#", "points": [[176, 260], [1460, 260], [1460, 2058], [176, 2058]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/信科科管〔2019〕65号-中国铁路信息科技集团有限公司关于印发《铁路信息系统运行维护计划管理规定》的通知_页面_3.jpg [{"transcription": "福", "points": [[267, 397], [2242, 397], [2242, 3056], [267, 3056]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_08.jpg [{"transcription": "e", "points": [[196, 135], [1457, 135], [1457, 2063], [196, 2063]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_03.jpg [{"transcription": "#", "points": [[171, 269], [1532, 269], [1532, 2013], [171, 2013]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_15.jpg [{"transcription": "待识别", "points": [[151, 266], [1471, 266], [1, 2013], [151, 2013]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_14.jpg [{"transcription": "待识别", "points": [[185, 277], [1507, 277], [7, 1183], [185, 1183]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[185, 277], [1507, 277], [1507, 1183], [185, 1183]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_1.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [08], [2153, 1016], [344, 1016]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022]10号", "points": [[878, 1183], [1632, 1183], [1632, 1320], [878, 1320]], "difficult": false, "key_cls": "文scription": "《仅联信显续换结总技权中心T发)通", "points": [[311, 1512], [2236, 1512], [2236, 1862], [311, 1862]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 1891], [2203,[2203, 2462], [299, 2462]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1274, 2724], [1994, 2724], [1994, 2824], [1274, 2824]], "difficult": false, "key_cls": "通知ption": "2022年9月26日", "points": [[1390, 2854], [1890, 2854], [1890, 2929], [1390, 2929]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_1.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [08], [2153, 1016], [344, 1016]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022]10号", "points": [[878, 1183], [1632, 1183], [1632, 1320], [878, 1320]], "difficult": false, "key_cls": "文scription": "《仅联信显续换结总技权中心T发)通", "points": [[311, 1512], [2236, 1512], [2236, 1862], [311, 1862]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 1891], [2203,299, 2462]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1274, 2724], [1994, 2724], [1994, 2824], [1274, 2824]], "difficult": false, "key_cls": "通知部门"}, {"trans月26日", "points": [[1390, 2854], [1890, 2854], [1890, 2929], [1390, 2929]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_10.jpg [{"transcription": "A", "points": [[176, 130], [1476, 130], [1476, 2060], [176, 2060]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_05.jpg [{"transcription": "福", "points": [[171, 252], [1465, 252], [1465, 1991],[171, 1991]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [[329, 816], [2154, 816], [2154, 1029], [329, 1029]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技网技［2022］16号", "points": [[858, 1191],58, 1316]], "difficult": false, "key_cls": "文号"}, {"transcription": "国铁集团信盘技术中心关产印发（伙路信息系域", "points": [[300, 1524], [2200, 1524], [2200, 1829], [300, 1829]], "difficult": false, "key_cls": "通知与)种", "points": [[292, 1883], [2213, 1883], [2213, 2245], [292, 2245]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1292, 2516], [2004, 2516], [2004, 2637], [1292cult": false, "key_cls": "通知部门"}, {"transcription": "2022年10月14日", "points": [[1350, 2666], [1908, 2666], [1908, 2749], [1350, 2749]], "difficult": false, "key_cls": "通知时间"}, {"transcription": "用和对北件岛工网、手机、微信够传播性", "points": [[250, 2824], [2283, 2824], [2283, 3079], [250, 3079]], "difficult": false, "key_cls": "其他"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_1.jpg [{"transcription": "中国铁路信息科技集团有限公司文件", "points": [[275, 78 [2192, 1045], [275, 1045]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信科研建［2023］ 46号", "points": [[842, 1216], [1650, 1216], [1650, 1370], [842, 1370]], "difficult": false, "key_cls": "文号iption": ",", "points": [[400, 1549], [2121, 1549], [2121, 2004], [400, 2004]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[271, 2049], [2167, 2049], [2167, 2449], [271, 2449]]cult": false, "key_cls": "通知内容"}, {"transcription": "中国铁路信息科技集团有限公司", "points": [[1200, 2741], [2108, 2741], [2108, 2841], [1200, 2841]], "difficult": false, "key_cls": "通知部门"}, {"transcription": : [[1388, 2879], [1913, 2879], [1913, 2974], [1388, 2974]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_16.jpg [{"transcription": "待识别", "points": [[176, 271], [1443, 271], [3, 2052], [176, 2052]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[176, 271], [1443, 271], [1443, 2052], [176, 2052]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《中国国家铁路集团有限公司信息技术中心评审专家遴选办法》的通知(信技网技〔2023〕6号)_页面_4.jpg [{"transcription": "店", "points": [[178, 266], [1464, 266], [1464, 2074], [178, 2074]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_1.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [08], [2153, 1016], [344, 1016]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022]10号", "points": [[878, 1183], [1632, 1183], [1632, 1320], [878, 1320]], "difficult": false, "key_cls": "文scription": "《仅联信显续换结总技权中心T发)通", "points": [[311, 1512], [2236, 1512], [2236, 1862], [311, 1862]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 1891], [2203,[2203, 2462], [299, 2462]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1274, 2724], [1994, 2724], [1994, 2824], [1274, 2824]], "difficult": false, "key_cls": "通知ption": "2022年9月26日", "points": [[1390, 2854], [1890, 2854], [1890, 2929], [1390, 2929]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_09.jpg [{"transcription": "店", "points": [[193, 271], [1493, 271], [1493 2063], [193, 2063]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_20.jpg [{"transcription": "待识别", "points": [[174, 260], [1476, 260], [1476, 2060], [174, 2060]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[174, 260], [1476, 260], [1476, 2060], [174, 2060]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_13.jpg [{"transcription": "商", "points": [[171, 249], [1490, 249], [1490 2021], [171, 2021]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [20], [2128, 1037], [307, 1037]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］8号", "points": [[844, 1179], [1599, 1179], [1599, 1312], [844, 1312]], "difficult": false, "key_cls": "文cription": "2", "points": [[315, 1470], [2178, 1470], [2178, 1974], [315, 1974]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 2020], [2186, 2020], [2186, 2595], [299, 2595"difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1294, 2858], [1994, 2858], [1994, 2966], [1294, 2966]], "difficult": false, "key_cls": "通知部门"}, {"transcription": "2s": [[1394, 2987], [1928, 2987], [1928, 3104], [1394, 3104]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_02.jpg [{"transcription": "铁路通用 PaaS 平台技术条件（试行）", "points": [[204, 663], [1440, 663], [1440, 808], [204, 808]], "difficult": false, "key_cls": "制度名称"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_7.jpg [{"transcription": "待识别", "points": [[171, 266], [1499, 266], [1499, 20, [171, 2030]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《中国国家铁路集团有限公司信息技术中心评审专家遴选办法》的通知(信技网技〔2023〕6号)_页面_5.jpg [{"transcription": "待识别", "points": [[173, 255], [1492, 255], [1492, 2063], [173, 2063]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/信科科管〔2019〕65号-中国铁路信息科技集团有限公司关于印发《铁路信息系统运行维护计划管理规定》的通知_页面_6.jpg [{"transcription": "无法识别", "points": [[312, 410], [2262, 410], [2262, 1531], [312, 1531]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "中国铁路信息科技集团有限公司办公室", "points": [[287, 2964], [1346, 293089]], "difficult": false, "key_cls": "发布部门"}, {"transcription": "2019年12月6日", "points": [[1546, 2977], [2033, 2977], [2033, 3064], [1546, 3064]], "difficult": false, "key_cls": "发布时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_08.jpg [{"transcription": "待识别", "points": [[165, 266], [1471, 266], [1471, 20, [165, 2041]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[165, 266], [1471, 266], [1471, 2041], [165, 2041]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《中国国家铁路集团有限公司信息技术中心评审专家遴选办法》的通知(信技网技〔2023〕6号)_页面_3.jpg [{"transcription": "0", "points": [[156, 269], [1520, 269], [1520, 2071], [156, 2071]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_07.jpg [{"transcription": "E", "points": [[185, 205], [1451, 205], [1451, 1871], [185, 1871]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_10.jpg [{"transcription": "A", "points": [[176, 130], [1476, 130], [1476, 2060], [176, 2060]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团网信专家库管理工作细则_页面_11.jpg [{"transcription": "1元", "points": [[174, 249], [1488, 249], [1488, 1983], [174, 983]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_11.jpg [{"transcription": "福", "points": [[165, 233], [1504, 233], [1504, 2041],[165, 2041]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [74], [2165, 1045], [349, 1045]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］9号", "points": [[857, 1179], [1590, 1179], [1590, 1329], [857, 1329]], "difficult": false, "key_cls": "文cription": "《铁路通质集四信技术心关于有)的通知", "points": [[290, 1524], [2257, 1524], [2257, 1866], [290, 1866]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[261, 1891], [226261, 2441]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1286, 2712], [1974, 2712], [1974, 2799], [1286, 2799]], "difficult": false, "key_cls": "通知部门"}, {"trans月26日", "points": [[1386, 2854], [1886, 2854], [1886, 2933], [1386, 2933]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_5.jpg [{"transcription": "一", "points": [[154, 249], [1510, 249], [1510, 1602],[154, 1602]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_02.jpg [{"transcription": "铁路应用系统运行时环境技术要求（试行）", "points": [[30], [1235, 994], [393, 994]], "difficult": false, "key_cls": "制度名称"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_09.jpg [{"transcription": "店", "points": [[193, 271], [1493, 271], [1493 2063], [193, 2063]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_03.jpg [{"transcription": "二", "points": [[146, 263], [1510, 263], [1510, 2074],[146, 2074]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团网信专家库管理工作细则_页面_03.jpg [{"transcription": "国", "points": [[171, 252], [1515, 252], [1515, 2083], [171, 283]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_11.jpg [{"transcription": "福", "points": [[165, 233], [1504, 233], [1504, 2041],[165, 2041]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_1.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [08], [2153, 1016], [344, 1016]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022]10号", "points": [[878, 1183], [1632, 1183], [1632, 1320], [878, 1320]], "difficult": false, "key_cls": "文scription": "《仅联信显续换结总技权中心T发)通", "points": [[311, 1512], [2236, 1512], [2236, 1862], [311, 1862]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 1891], [2203,299, 2462]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1274, 2724], [1994, 2724], [1994, 2824], [1274, 2824]], "difficult": false, "key_cls": "通知部门"}, {"trans月26日", "points": [[1390, 2854], [1890, 2854], [1890, 2929], [1390, 2929]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_14.jpg [{"transcription": "待识别", "points": [[185, 277], [1507, 277], [7, 1183], [185, 1183]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[185, 277], [1507, 277], [1507, 1183], [185, 1183]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [20], [2128, 1037], [307, 1037]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］8号", "points": [[844, 1179], [1599, 1179], [1599, 1312], [844, 1312]], "difficult": false, "key_cls": "文cription": "2", "points": [[315, 1470], [2178, 1470], [2178, 1974], [315, 1974]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 2020], [2186, 2020], [2186, 2595], [299, 2595ficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1294, 2858], [1994, 2858], [1994, 2966], [1294, 2966]], "difficult": false, "key_cls": "通知部门"}, {"transcription": "2022年s": [[1394, 2987], [1928, 2987], [1928, 3104], [1394, 3104]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_08.jpg [{"transcription": "待识别", "points": [[165, 266], [1471, 266], [1471, 20, [165, 2041]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[165, 266], [1471, 266], [1471, 2041], [165, 2041]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_10.jpg [{"transcription": "店", "points": [[185, 280], [1521, 280], [1521, 2069], [185, 2069]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_04.jpg [{"transcription": "待识别", "points": [[173, 266], [1550, 266], [1550, 1835], [173, 1835]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[173, 266], [1550, 266], [1550, 1835], [173, 1835]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_1.jpg [{"transcription": "中国铁路信息科技集团有限公司文件", "points": [[275, 78 [2192, 1045], [275, 1045]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信科研建［2023］ 46号", "points": [[842, 1216], [1650, 1216], [1650, 1370], [842, 1370]], "difficult": false, "key_cls": "文号iption": ",", "points": [[400, 1549], [2121, 1549], [2121, 2004], [400, 2004]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[271, 2049], [2167, 2049], [2167, 2449], [271, 2449]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "中国铁路信息科技集团有限公司", "points": [[1200, 2741], [2108, 2741], [2108, 2841], [1200, 2841]], "difficult": false, "key_cls": "通知部门"}, {"transcri"points": [[1388, 2879], [1913, 2879], [1913, 2974], [1388, 2974]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_02.jpg [{"transcription": "铁路通用 PaaS 平台技术条件（试行）", "points": [[204, 63], [1440, 808], [204, 808]], "difficult": false, "key_cls": "制度名称"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_24.jpg [{"transcription": "国铁集团信息技术中心", "points": [[235, 1949], [668, 1949], [668, 2002], [235, 2002]], "difficult": false, "key_cls": "发布部门"}, {"transcription": "2022年10月17日", "points": [[988, 1941], [1329, 1941], [1329, 1999"difficult": false, "key_cls": "发布时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_03.jpg [{"transcription": "待识别", "points": [[173, 288], [1548, 288], [1548, 2069], [173, 2069]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[173, 288], [1548, 288], [1548, 2069], [173, 2069]], "difffalse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_3.jpg [{"transcription": "S", "points": [[140, 344], [1538, 344], [1538, 1849], [140, 1849]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_18.jpg [{"transcription": "待识别", "points": [[179, 271], [1510, 271], [1510, 2074], [179, 2074]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[179, 271], [1510, 271], [1510, 2074], [179, 2074]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_05.jpg [{"transcription": "6", "points": [[179, 205], [1479, 205], [1479, 2066], [179, 2066]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [[329, 816], [2154, 816], [2154, 1029], [329, 1029]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技网技［2022］16号", "points": [[858, 1191],58, 1316]], "difficult": false, "key_cls": "文号"}, {"transcription": "国铁集团信盘技术中心关产印发（伙路信息系域", "points": [[300, 1524], [2200, 1524], [2200, 1829], [300, 1829]], "difficult": false, "key_cls": "通知与)种", "points": [[292, 1883], [2213, 1883], [2213, 2245], [292, 2245]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1292, 2516], [2004, 2516], [2004, 2637], [1292ficult": false, "key_cls": "通知部门"}, {"transcription": "2022年10月14日", "points": [[1350, 2666], [1908, 2666], [1908, 2749], [1350, 2749]], "difficult": false, "key_cls": "通知时间"}, {"transcription": "用和对北件岛微信够传播性", "points": [[250, 2824], [2283, 2824], [2283, 3079], [250, 3079]], "difficult": false, "key_cls": "其他"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/信科科管〔2019〕65号-中国铁路信息科技集团有限公司关于印发《铁路信息系统运行维护计划管理规定》的通知_页面_3.jpg [{"transcription": "福", "points": [[267, 397], [2242, 397], [2242, 3056], [267, 3056]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_16.jpg [{"transcription": "待识别", "points": [[176, 271], [1443, 271], [3, 2052], [176, 2052]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[176, 271], [1443, 271], [1443, 2052], [176, 2052]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:07] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_13.jpg [{"transcription": "商", "points": [[171, 249], [1490, 249], [1490 2021], [171, 2021]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_24.jpg [{"transcription": "国铁集团信息技术中心", "points": [[235, 1949], [668, 1949], [668, 2002], [235, 2002]], "difficult": false, "key_cls": "发布部门"}, {"transcription": "2022年10月17日", "points": [[988, 1941], [1329, 1941], [1329, 1999"difficult": false, "key_cls": "发布时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_02.jpg [{"transcription": "铁路通用 PaaS 平台技术条件（试行）", "points": [[204, 63], [1440, 808], [204, 808]], "difficult": false, "key_cls": "制度名称"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_5.jpg [{"transcription": "国", "points": [[189, 263], [1470, 263], [1470, 2069],[189, 2069]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_19.jpg [{"transcription": "待识别", "points": [[190, 271], [1482, 271], [2, 1630], [190, 1630]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[190, 271], [1482, 271], [1482, 1630], [190, 1630]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统双活架构设计指南（试行）_页面_3.jpg [{"transcription": "S", "points": [[140, 344], [1538, 344], [1538, 1849], [140, 1849]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/信科科管〔2019〕65号-中国铁路信息科技集团有限公司关于印发《铁路信息系统运行维护计划管理规定》的通知_页面_5.jpg [{"transcription": "店", "points": [[233, 431], [2192, 431], [2192, 3052], [233, 3052]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_6.jpg [{"transcription": "际", "points": [[173, 258], [1470, 258], [1470, 2049],[173, 2049]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_02.jpg [{"transcription": "铁路通用 PaaS 平台技术条件（试行）", "points": [[204, 63], [1440, 808], [204, 808]], "difficult": false, "key_cls": "制度名称"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_15.jpg [{"transcription": "待识别", "points": [[151, 266], [1471, 266], [1, 2013], [151, 2013]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [74], [2165, 1045], [349, 1045]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］9号", "points": [[857, 1179], [1590, 1179], [1590, 1329], [857, 1329]], "difficult": false, "key_cls": "文"}, {"transcription": "《铁路通质集四信技术心关于有)的通知", "points": [[290, 1524], [2257, 1524], [2257, 1866], [290, 1866]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[261, 1, 2441], [261, 2441]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1286, 2712], [1974, 2712], [1974, 2799], [1286, 2799]], "difficult": false, "key_cls": "通知部门n": "2022年9月26日", "points": [[1386, 2854], [1886, 2854], [1886, 2933], [1386, 2933]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_22.jpg [{"transcription": "待识别", "points": [[171, 260], [1507, 260], [1507, 2066], [171, 2066]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[171, 260], [1507, 260], [1507, 2066], [171, 2066]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_20.jpg [{"transcription": "待识别", "points": [[174, 260], [1476, 260], [1476, 2060], [174, 2060]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[174, 260], [1476, 260], [1476, 2060], [174, 2060]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团网信专家库管理工作细则_页面_03.jpg [{"transcription": "国", "points": [[171, 252], [1515, 252], [1515, 2083], [171, 283]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_18.jpg [{"transcription": "待识别", "points": [[168, 246], [1549, 246], [549, 1108], [168, 1108]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[168, 246], [1549, 246], [1549, 1108], [168, 1108]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《中国国家铁路集团有限公司信息技术中心评审专家遴选办法》的通知(信技网技〔2023〕6号)_页面_6.jpg [{"transcription": "无法识别", "points": [[91, 103], [733, 103], [733, 322], [91, 322]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "国铁集团信息技术中心", "points": [[114, 805], [319, 805], [319, 837], [114, 837]], "difficult": false, "key_cls": "发布部门"}, {"transcription": "2023年6月20日", "points": [[477, 807], [634, 807], [634, 833], [477, 833]], "difficult": false, "key_cls": "发布时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《中国国家铁路集团有限公司信息技术中心评审专家遴选办法》的通知(信技网技〔2023〕6号)_页面_5.jpg [{"transcription": "待识别", "points": [[173, 255], [1492, 255], [1492, 2063], [173, 2063]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [74], [2165, 1045], [349, 1045]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］9号", "points": [[857, 1179], [1590, 1179], [1590, 1329], [857, 1329]], "difficult": false, "key_cls": "文cription": "《铁路通质集四信技术心关于有)的通知", "points": [[290, 1524], [2257, 1524], [2257, 1866], [290, 1866]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[261, 1891], [226261, 2441]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1286, 2712], [1974, 2712], [1974, 2799], [1286, 2799]], "difficult": false, "key_cls": "通知部门"}, {"trans月26日", "points": [[1386, 2854], [1886, 2854], [1886, 2933], [1386, 2933]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_04.jpg [{"transcription": "待识别", "points": [[173, 266], [1550, 266], [1550, 1835], [173, 1835]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[173, 266], [1550, 266], [1550, 1835], [173, 1835]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_07.jpg [{"transcription": "待识别", "points": [[146, 269], [1513, 269], [3, 2083], [146, 2083]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/信科科管〔2019〕65号-中国铁路信息科技集团有限公司关于印发《铁路信息系统运行维护计划管理规定》的通知_页面_3.jpg [{"transcription": "福", "points": [[267, 397], [2242, 397], [2242, 3056], [267, 3056]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_18.jpg [{"transcription": "待识别", "points": [[179, 271], [1510, 271], [1510, 2074], [179, 2074]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[179, 271], [1510, 271], [1510, 2074], [179, 2074]], "diffse, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [74], [2165, 1045], [349, 1045]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］9号", "points": [[857, 1179], [1590, 1179], [1590, 1329], [857, 1329]], "difficult": false, "key_cls": "文cription": "《铁路通质集四信技术心关于有)的通知", "points": [[290, 1524], [2257, 1524], [2257, 1866], [290, 1866]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[261, 1891], [226261, 2441]], "difficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1286, 2712], [1974, 2712], [1974, 2799], [1286, 2799]], "difficult": false, "key_cls": "通知部门"}, {"trans月26日", "points": [[1386, 2854], [1886, 2854], [1886, 2933], [1386, 2933]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_7.jpg [{"transcription": "待识别", "points": [[167, 260], [1523, 260], [1523, 11, [167, 1116]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[167, 260], [1523, 260], [1523, 1116], [167, 1116]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_04.jpg [{"transcription": "待识别", "points": [[154, 255], [1582, 255], [1582, 54 [154, 541]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[154, 255], [1582, 255], [1582, 541], [154, 541]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_01.jpg [{"transcription": "中国国家铁路集团有限公司信息技术中心文件", "points": [20], [2128, 1037], [307, 1037]], "difficult": false, "key_cls": "文件抬头"}, {"transcription": "信技研建［2022］8号", "points": [[844, 1179], [1599, 1179], [1599, 1312], [844, 1312]], "difficult": false, "key_cls": "文cription": "2", "points": [[315, 1470], [2178, 1470], [2178, 1974], [315, 1974]], "difficult": false, "key_cls": "通知名称"}, {"transcription": "无法识别", "points": [[299, 2020], [2186, 2020], [2186, 2595], [299, 2595ficult": false, "key_cls": "通知内容"}, {"transcription": "国铁集团信息技术中心", "points": [[1294, 2858], [1994, 2858], [1994, 2966], [1294, 2966]], "difficult": false, "key_cls": "通知部门"}, {"transcription": "2022年oints": [[1394, 2987], [1928, 2987], [1928, 3104], [1394, 3104]], "difficult": false, "key_cls": "通知时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_10.jpg [{"transcription": "A", "points": [[176, 130], [1476, 130], [1476, 2060], [176, 2060]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路信息系统运行时环境技术要求（试行）_页面_02.jpg [{"transcription": "铁路应用系统运行时环境技术要求（试行）", "points": [[30], [1235, 994], [393, 994]], "difficult": false, "key_cls": "制度名称"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_3.jpg [{"transcription": "M", "points": [[173, 258], [1450, 258], [1450, 2069], [173, 2069]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_8.jpg [{"transcription": "中国铁路信息科技集团有限公司办公室", "points": [[118, [444, 911], [118, 911]], "difficult": false, "key_cls": "发布部门"}, {"transcription": "2023年8月31日", "points": [[481, 882], [639, 882], [639, 909], [481, 909]], "difficult": false, "key_cls": "发布时间"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团网信专家库管理工作细则_页面_02.jpg [{"transcription": "国铁集团网络安企和信息化专家库管理工作细则（试行）", "points":, [1307, 638], [357, 638]], "difficult": false, "key_cls": "制度名称"}, {"transcription": "广", "points": [[146, 677], [1557, 677], [1557, 2091], [146, 2091]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团应用系统研发项目日常管理实施细则_页面_03.jpg [{"transcription": "#", "points": [[171, 269], [1532, 269], [1532, 2013], [171, 2013]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/关于规范信息系统研发工作的指导意见_页面_6.jpg [{"transcription": "际", "points": [[173, 258], [1470, 258], [1470, 2049],[173, 2049]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_17.jpg [{"transcription": "L", "points": [[163, 271], [1496, 271], [1496, 2063], [163, 2063]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/国铁集团信息技术中心关于印发《铁路信息系统运行维护日常管理细则（试行）》的通知-信技网技16_页面_18.jpg [{"transcription": "待识别", "points": [[179, 271], [1510, 271], [1510, 2074], [179, 2074]], "difficult": false, "key_cls": "制度内容"}, {"transcription": "无法识别", "points": [[179, 271], [1510, 271], [1510, 2074], [179, 2074]], "difficult": false, "key_cls": "制度内容"}]
, error happened with msg: Traceback (most recent call last):
File "/home/wyy/railway/PaddleOCR/ppocr/data/simple_dataset.py", line 139, in getitem
outs = transform(data, self.ops)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/init.py", line 72, in transform
data = op(data)
File "/home/wyy/railway/PaddleOCR/ppocr/data/imaug/label_ops.py", line 1171, in call
label = info["label"]
KeyError: 'label'

[2024/11/06 16:15:08] ppocr ERROR: When parsing line /home/wyy/railway/train_data/det/train/铁路通用PaaS平台技术条件（试行）_页面_10.jpg [{"transcription": "A", "points": [[176, 13^CLAUNCH INFO 2024-11-06 16:15:09,873 Terminating with signal 2
^CLAUNCH INFO 2024-11-06 16:15:10,141 Force quit in 10 seconds...
^CLAUNCH INFO 2024-11-06 16:15:10,389 Force quit in 10 seconds...
^C
Uploading TR-PPOCRLabel标注处理后.zip…

[GreatV]

根据报错信息和问题描述，KeyError: 'label' 是因为在 PaddleOCR 的数据加载过程中，某些数据缺少 label 字段或字段格式不正确。以下是可能的原因及解决方案：

---

问题原因分析

1. 标注文件格式错误

   • 从日志中可以看到，PPOCRLabel 生成的标注文件中，某些数据的 JSON 格式不符合预期。例如：

     [{"transcription": "待识别", "points": [[154, 255], [1582, 255], [1582, 541], [154, 541]], "difficult": false, "key_cls": "制度内容"}]

     缺少 label 字段，而当前模型或数据加载器期望每条数据包含 label。

2. 标注文件中的坐标问题

   • 某些数据的 points 坐标格式可能存在语法错误，例如：

     [{"transcription": "待识别", "points": [[154, 255], [1582, 255], [1582, 54 [154, 541]], "difficult": false}]

     points 的括号不匹配，导致 JSON 无法正常解析。

3. 模型配置与数据不匹配

   • 配置文件中定义的数据处理操作（KeepKeys）需要 labels 字段，但数据中没有提供此字段。例如：

     KeepKeys:
       keep_keys: ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels']

     如果标注文件中没有 labels，就会触发 KeyError: 'label'。

4. PPOCRLabel 的标注不完整

   • 可能在使用 PPOCRLabel 工具标注数据时，部分标注未保存或标注过程中出现错误，导致标注文件缺少必要字段。

---

解决方案

1. 检查标注文件

• 检查训练集和验证集的标注文件是否符合模型的要求。标注文件应为 JSON 格式，且每条数据必须包含 label 或 labels 字段。例如：

  {
      "transcription": "文本内容",
      "points": [[x1, y1], [x2, y2], [x3, y3], [x4, y4]],
      "label": "类别名称"
  }

• 如果标注文件缺少 label 字段，可以通过脚本补充。例如：

  import json
  
  def fix_labels(file_path):
      with open(file_path, 'r', encoding='utf-8') as f:
          data = json.load(f)
  
      for item in data:
          if 'label' not in item:
              item['label'] = "default"  # 添加默认标签
  
      with open(file_path, 'w', encoding='utf-8') as f:
          json.dump(data, f, ensure_ascii=False, indent=4)
  
  fix_labels("train.json")

2. 修复标注文件的语法错误

• 检查 points 坐标的完整性，确保每个 points 的值是四个 [x, y] 点，并且格式正确。
• 可以通过以下脚本检查标注文件是否有格式错误：

  import json
  
  def validate_annotations(file_path):
      with open(file_path, 'r', encoding='utf-8') as f:
          data = json.load(f)
  
      for i, item in enumerate(data):
          try:
              assert 'points' in item, f"Missing 'points' in item {i}"
              assert len(item['points']) == 4, f"Invalid 'points' length in item {i}"
              assert 'label' in item, f"Missing 'label' in item {i}"
          except AssertionError as e:
              print(f"Error in item {i}: {e}")
  
  validate_annotations("train.json")

3. 修改模型配置

• 如果标注文件中字段名与模型配置不一致（例如标注文件使用 key_cls 而非 label），可以修改配置文件中的 KeepKeys：

  KeepKeys:
    keep_keys: ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'key_cls']

4. 重新生成标注文件

• 若标注文件问题较多，建议重新使用 PPOCRLabel 工具标注数据，确保标注文件完整并符合格式要求。

5. 验证标注文件与模型的一致性

• 确保标注文件中的类别名称与配置文件中定义的类别一致。例如：
  • 配置文件中的 class_path：

    VQATokenLabelEncode:
      class_path: ./train_data/TR4/TR4_label.txt

  • TR4_label.txt 文件内容应与标注文件中的 label 字段一致：

    类别1
    类别2
    类别3
    

6. 检查 PPOCRLabel 导出的标注

• 如果问题出现在 PPOCRLabel 导出的标注文件，可以尝试更新 PaddleOCR 和 PPOCRLabel 工具，确保使用的是最新版本：

  pip install --upgrade paddleocr

7. 忽略错误数据

• 如果某些标注数据始终存在问题，可以在训练时自动跳过这些数据：

  try:
      data = transform(data, self.ops)
  except KeyError as e:
      print(f"Skipping problematic data: {e}")
      continue

---

参考资料

• PaddleOCR Discussions: PPOCRLabel标注后的数据导入Vi-Layoutxlm报错
• PaddleOCR Issues: 标注数据报错 KeyError

---

总结

• 标注文件检查和修复 是解决该问题的关键。
• 确保标注文件字段完整且符合模型的配置要求。
• 必要时重新生成标注文件或调整模型配置以适配数据。

如果问题仍然存在，可以提供更多的标注文件样例和配置文件内容，进一步分析问题。

---

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