首页 Paddle框架 帖子详情
PPOCR训练识别模型报错with msg: Traceback (most recent call last) 已解决
收藏
快速回复
Paddle框架 问答模型训练 3763 14
PPOCR训练识别模型报错with msg: Traceback (most recent call last) 已解决
收藏
快速回复
Paddle框架 问答模型训练 3763 14

识别数据是我自己写的工具自动生成标注,自动确认的。

生成好的数据,能被官方标注工具识别,能正常导出,正常裁剪。

由工具导出后,无规律的出现以下问题。但是只要我修改最后一行,他就有时候会出现下面问题,有时候不会出现,测试,

如果是用官方的自动标注,则不会出现,这个问题。现在很郁闷了,标注的格式是完全一样的。分隔符也是对的。

 

 

[2022/08/04 16:29:49] ppocr INFO: epoch: [8/800], global_step: 50, lr: 0.000494, acc: 0.000000, norm_edit_dis: 0.178335, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.060363, dml_ctc_0: 3.239076, loss: 565.145874, dml_sar_0: 1.614317, loss_distance_l2_Student_Teacher_0: 0.108743, loss_ctc_Student_0: 275.429382,
loss_ctc_Teacher_1: 279.299194, loss_sar_Student_0: 2.912240, loss_sar_Teacher_1: 2.859969, avg_reader_cost: 29.12216 s, avg_batch_cost: 25.57256 s, avg_samples: 16.0, ips: 0.62567 samples/s, eta: 1 day, 22:08:12
[2022/08/04 16:30:06] ppocr ERROR: When parsing line crop_img/1659537347217_crop_7.jpg 硕奢盔匾颅彪眶晤曼晦冕啡畦趾啃蛆蚯蛉蛀唬啰唾啤啥啸
, error happened with msg: Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 137, in __getitem__
outs = transform(data, self.ops)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\__init__.py", line 50, in transform
data = op(data)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\rec_img_aug.py", line 31, in __call__
img = warp(img, 10, self.use_tia, self.aug_prob)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\rec_img_aug.py", line 580, in warp
new_img = tia_perspective(new_img)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\augment.py", line 118, in tia_perspective
dst = trans.generate()
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\warp_mls.py", line 42, in generate
return self.gen_img()
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\warp_mls.py", line 148, in gen_img
nx = np.clip(nx, 0, src_w - 1)
File "<__array_function__ internals>", line 180, in clip
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 2154, in clip
return _wrapfunc(a, 'clip', a_min, a_max, out=out, **kwargs)
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 57, in _wrapfunc
return bound(*args, **kwds)
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\_methods.py", line 135, in _clip
if _clip_dep_is_scalar_nan(min):
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\_methods.py", line 95, in _clip_dep_is_scalar_nan
if ndim(a) != 0:
File "<__array_function__ internals>", line 180, in ndim
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 3154, in ndim
return a.ndim
RecursionError: maximum recursion depth exceeded while calling a Python object

[2022/08/04 16:32:34] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:34:09] ppocr INFO: epoch: [9/800], global_step: 60, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.211760, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.136314, dml_ctc_0: 3.059824, loss: 539.750488, dml_sar_0: 1.637128, loss_distance_l2_Student_Teacher_0: 0.081149, loss_ctc_Student_0: 264.262329,
loss_ctc_Teacher_1: 265.207367, loss_sar_Student_0: 2.508176, loss_sar_Teacher_1: 2.390895, avg_reader_cost: 27.72804 s, avg_batch_cost: 25.95874 s, avg_samples: 16.0, ips: 0.61636 samples/s, eta: 1 day, 21:59:25
[2022/08/04 16:35:27] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:35:28] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\iter_epoch_9
[2022/08/04 16:38:17] ppocr INFO: epoch: [10/800], global_step: 70, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.245510, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.205209, dml_ctc_0: 3.150162, loss: 515.714539, dml_sar_0: 1.507585, loss_distance_l2_Student_Teacher_0: 0.069946, loss_ctc_Student_0: 252.565979,
loss_ctc_Teacher_1: 253.574463, loss_sar_Student_0: 2.207326, loss_sar_Teacher_1: 2.276554, avg_reader_cost: 26.14409 s, avg_batch_cost: 24.80599 s, avg_samples: 16.0, ips: 0.64501 samples/s, eta: 1 day, 21:34:26
[2022/08/04 16:38:39] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:41:40] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:42:43] ppocr INFO: epoch: [12/800], global_step: 80, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.263455, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.246941, dml_ctc_0: 3.573940, loss: 485.858093, dml_sar_0: 1.547996, loss_distance_l2_Student_Teacher_0: 0.050314, loss_ctc_Student_0: 238.444138,
loss_ctc_Teacher_1: 238.176086, loss_sar_Student_0: 2.105234, loss_sar_Teacher_1: 2.107480, avg_reader_cost: 29.45733 s, avg_batch_cost: 26.61069 s, avg_samples: 16.0, ips: 0.60126 samples/s, eta: 1 day, 21:37:51
[2022/08/04 16:44:55] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:44:57] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\iter_epoch_12
[2022/08/04 16:46:58] ppocr INFO: epoch: [13/800], global_step: 90, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.271702, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.277518, dml_ctc_0: 4.186323, loss: 462.295654, dml_sar_0: 1.623069, loss_distance_l2_Student_Teacher_0: 0.040496, loss_ctc_Student_0: 225.776047,
loss_ctc_Teacher_1: 225.721954, loss_sar_Student_0: 2.067064, loss_sar_Teacher_1: 2.042954, avg_reader_cost: 27.86247 s, avg_batch_cost: 25.45313 s, avg_samples: 16.0, ips: 0.62861 samples/s, eta: 1 day, 21:26:16
[2022/08/04 16:47:39] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:50:33] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:51:34] ppocr INFO: epoch: [15/800], global_step: 100, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.300474, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.305811, dml_ctc_0: 5.125176, loss: 436.638245, dml_sar_0: 1.602562, loss_distance_l2_Student_Teacher_0: 0.036041, loss_ctc_Student_0: 213.821365
, loss_ctc_Teacher_1: 214.328674, loss_sar_Student_0: 1.970798, loss_sar_Teacher_1: 1.957318, avg_reader_cost: 32.29417 s, avg_batch_cost: 27.60091 s, avg_samples: 16.0, ips: 0.57969 samples/s, eta: 1 day, 21:38:07
[2022/08/04 16:53:45] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:53:46] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\iter_epoch_15
[2022/08/04 16:55:20] ppocr INFO: epoch: [16/800], global_step: 110, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.345662, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.337741, dml_ctc_0: 6.407097, loss: 417.100555, dml_sar_0: 1.607420, loss_distance_l2_Student_Teacher_0: 0.033268, loss_ctc_Student_0: 202.756073
, loss_ctc_Teacher_1: 203.013443, loss_sar_Student_0: 1.867772, loss_sar_Teacher_1: 1.829765, avg_reader_cost: 24.45391 s, avg_batch_cost: 22.64230 s, avg_samples: 16.0, ips: 0.70664 samples/s, eta: 1 day, 21:00:07
[2022/08/04 16:56:30] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:59:29] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 16:59:45] ppocr INFO: epoch: [18/800], global_step: 120, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.365049, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.364450, dml_ctc_0: 8.299166, loss: 393.431885, dml_sar_0: 1.484911, loss_distance_l2_Student_Teacher_0: 0.033393, loss_ctc_Student_0: 190.124557
, loss_ctc_Teacher_1: 188.099655, loss_sar_Student_0: 1.954345, loss_sar_Teacher_1: 1.802374, avg_reader_cost: 30.70261 s, avg_batch_cost: 26.45036 s, avg_samples: 16.0, ips: 0.60491 samples/s, eta: 1 day, 21:00:27
[2022/08/04 17:02:06] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 17:02:08] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\iter_epoch_18
[2022/08/04 17:04:04] ppocr INFO: epoch: [19/800], global_step: 130, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.348358, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.413889, dml_ctc_0: 10.693516, loss: 376.424103, dml_sar_0: 1.518016, loss_distance_l2_Student_Teacher_0: 0.036367, loss_ctc_Student_0: 179.73376
5, loss_ctc_Teacher_1: 179.810242, loss_sar_Student_0: 1.887479, loss_sar_Teacher_1: 1.785832, avg_reader_cost: 26.86625 s, avg_batch_cost: 25.90003 s, avg_samples: 16.0, ips: 0.61776 samples/s, eta: 1 day, 20:55:57
[2022/08/04 17:05:32] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 17:08:13] ppocr INFO: epoch: [20/800], global_step: 140, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.334281, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.448844, dml_ctc_0: 11.575937, loss: 356.703796, dml_sar_0: 1.625040, loss_distance_l2_Student_Teacher_0: 0.037015, loss_ctc_Student_0: 170.61535
6, loss_ctc_Teacher_1: 170.659470, loss_sar_Student_0: 1.698452, loss_sar_Teacher_1: 1.746010, avg_reader_cost: 27.51520 s, avg_batch_cost: 24.96712 s, avg_samples: 16.0, ips: 0.64084 samples/s, eta: 1 day, 20:44:29
[2022/08/04 17:08:47] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 17:11:54] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 17:11:56] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\iter_epoch_21
[2022/08/04 17:13:14] ppocr INFO: epoch: [22/800], global_step: 150, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.332032, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.474219, dml_ctc_0: 13.204651, loss: 325.593079, dml_sar_0: 1.607670, loss_distance_l2_Student_Teacher_0: 0.028689, loss_ctc_Student_0: 157.24827
6, loss_ctc_Teacher_1: 154.950653, loss_sar_Student_0: 1.597282, loss_sar_Teacher_1: 1.628026, avg_reader_cost: 35.13871 s, avg_batch_cost: 30.03986 s, avg_samples: 16.0, ips: 0.53263 samples/s, eta: 1 day, 21:08:36
[2022/08/04 17:14:44] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 17:17:17] ppocr INFO: epoch: [23/800], global_step: 160, lr: 0.000500, acc: 0.000000, norm_edit_dis: 0.338211, Teacher_acc: 0.000000, Teacher_norm_edit_dis: 0.483507, dml_ctc_0: 15.968353, loss: 308.580231, dml_sar_0: 1.653899, loss_distance_l2_Student_Teacher_0: 0.022913, loss_ctc_Student_0: 145.54815
7, loss_ctc_Teacher_1: 142.429077, loss_sar_Student_0: 1.500686, loss_sar_Teacher_1: 1.560286, avg_reader_cost: 25.91323 s, avg_batch_cost: 24.31838 s, avg_samples: 16.0, ips: 0.65794 samples/s, eta: 1 day, 20:52:21
[2022/08/04 17:17:49] ppocr INFO: save model in ./output/rec_ppocr_v3_distillation\latest
[2022/08/04 17:20:18] ppocr ERROR: When parsing line crop_img/1659537344481_crop_7.jpg 累唱患唯崖崭崇圈铜铲银甜梨犁移笨笼笛符第敏做袋悠偿
, error happened with msg: Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 137, in __getitem__
outs = transform(data, self.ops)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\__init__.py", line 50, in transform
data = op(data)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\rec_img_aug.py", line 31, in __call__
img = warp(img, 10, self.use_tia, self.aug_prob)
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\rec_img_aug.py", line 571, in warp
new_img = tia_distort(new_img, random.randint(3, 6))
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\augment.py", line 60, in tia_distort
dst = trans.generate()
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\warp_mls.py", line 42, in generate
return self.gen_img()
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\warp_mls.py", line 148, in gen_img
nx = np.clip(nx, 0, src_w - 1)
File "<__array_function__ internals>", line 180, in clip
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 2154, in clip
return _wrapfunc(a, 'clip', a_min, a_max, out=out, **kwargs)
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 57, in _wrapfunc
return bound(*args, **kwds)
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\_methods.py", line 135, in _clip
if _clip_dep_is_scalar_nan(min):
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\_methods.py", line 95, in _clip_dep_is_scalar_nan
if ndim(a) != 0:
File "<__array_function__ internals>", line 180, in ndim
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 3154, in ndim
return a.ndim
RecursionError: maximum recursion depth exceeded while calling a Python object

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

Current thread 0x000067e8 (most recent call first):
File "<__array_function__ internals>", line 180 in ndim
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\_methods.py", line 95 in _clip_dep_is_scalar_nan
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\_methods.py", line 135 in _clip
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 57 in _wrapfunc
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\numpy\core\fromnumeric.py", line 2154 in clip
File "<__array_function__ internals>", line 180 in clip
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\warp_mls.py", line 148 in gen_img
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\warp_mls.py", line 42 in generate
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\text_image_aug\augment.py", line 94 in tia_stretch
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\rec_img_aug.py", line 576 in warp
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\rec_img_aug.py", line 31 in __call__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\imaug\__init__.py", line 50 in transform
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 137 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
File "C:\Users\Administrator\Desktop\OCR\ppocr\data\simple_dataset.py", line 147 in __getitem__
...

Thread 0x00007d40 (most recent call first):
File "C:\Users\Administrator\Desktop\OCR\venv\lib\site-packages\paddle\fluid\dataloader\dataloader_iter.py", line 272 in __next__
File "C:\Users\Administrator\Desktop\OCR\tools\program.py", line 243 in train
File "tools/train.py", line 166 in main
File "tools/train.py", line 193 in
PS C:\Users\Administrator\Desktop\OCR>

 

尝试解决1:

import sys
sys.setrecursionlimit(10000)

则不出现报错,但直接就退出了。

尝试解决2:

对比两个文本,检查格式,发现分割符确实一样。

尝试解决3:

把能训练的这个文本的最后一行复制给不能训练的这个问题,则报错不会立即出现。甚至可以开启训练(不知道能不能训练完)。

但删掉这行,立即报错。

这样的问题好离谱,不知道该怎么办了,现在考虑是不是字典的问题,谁遇到过能指点下吗?

 

582716403
已解决
4# 回复于2022-08
找到问题了。数据的原因。
0
收藏
回复
全部评论(14)
时间顺序
582716403
#2 回复于2022-08

还有个现象,如果是官方工具一键自动标注的,开启训练特别快,需要1.5天训练完。具体报不报错未知。

但用自己工具标注导出的,开启训练特别慢。需要4天半训练完,然后训练中途报上诉错误。

 

0
回复
582716403
#3 回复于2022-08

数据是官方工具的不能识别全部,但是我的工具全部标注了,而且非常准确。但总体量相差的并不大,大概是   7:10
导出识别数据,都是用的官方工具导出的,对比下来,标注的数据没有发现任何问题。

部分截图图片传不上来好烦啊

0
回复
582716403
#4 回复于2022-08

找到问题了。数据的原因。

0
回复
深渊上的坑
#5 回复于2022-08
找到问题了。数据的原因。

具体是什么样的数据问题呢?

0
回复
李长安
#6 回复于2022-08

估计是格式啥的吧

0
回复
c
cange4
#7 回复于2022-08

具体什么原因

0
回复
天之子丷
#8 回复于2022-09
找到问题了。数据的原因。

你好,请问一下,你这个最终会生成best开头的文件吗 ?还是最终就是last前缀文件

0
回复
Jonny5659
#9 回复于2023-01
找到问题了。数据的原因。

什么样的原因呢,求分享 我的症状这个有点像

0
回复
糖油粑粑
#10 回复于2023-03
什么样的原因呢,求分享 我的症状这个有点像

同问

0
回复
x
xpp123www
#11 回复于2023-04
同问

同问啊, 我用ppocrlabel标注的居然也出现了这个问题。 (一开始是自己按格式生产的,就怀疑是不是有不对的地方, 后来用ppocrlabel生成的数据集测试也有这个问题), 求指导啊

0
回复
AIStudio395906
#12 回复于2023-05
xpp123www #11
同问啊, 我用ppocrlabel标注的居然也出现了这个问题。 (一开始是自己按格式生产的,就怀疑是不是有不对的地方, 后来用ppocrlabel生成的数据集测试也有这个问题), 求指导啊

已解决:还是格式的问题呀。

将中间的空格改成paddlelabel生成的空格就行了。

 

0
回复
机械狂人wu
#13 回复于2023-09

已解决!!

标签的问题:PaddleOCR-new\ppocr\data\simple_dataset.py 152行 有一行代码 substr = data_line.strip("\n").split(self.delimiter) 其中参数self.delimiter是"\t",所以标签中图片名字和后边应该是以这个分隔的,这个和四个空格很相似。

0
回复
霖枫忆蓝
#14 回复于2024-04
已解决!! 标签的问题:PaddleOCR-new\ppocr\data\simple_dataset.py 152行 有一行代码 substr = data_line.strip("\n").split(self.delimiter) 其中参数self.delimiter是"\t",所以标签中图片名字和后边应该是以这个分隔的,这个和四个空格很相似。
展开

请问把self.delimiter改成“\t” 就好了吗   我改了会报其他错误

0
回复
5
54热血6P
#15 回复于2024-05
找到问题了。数据的原因。

您好!请问下是啥数据问题呢?我也遇到了

0
回复
需求/bug反馈?一键提issue告诉我们
发现bug?如果您知道修复办法,欢迎提pr直接参与建设飞桨~
在@后输入用户全名并按空格结束,可艾特全站任一用户