Out of memory error on GPU

[danbao12138]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 系统环境/System Environment：ubuntu18

• 版本号/Version：Paddle：2.2.1.post112 PaddleOCR：2.6.1.2 问题相关组件/Related components：ppstructure
  cuda11.3 +cudnn8.4 +paddlepaddle-gpu==2.2.1.post112 +paddleocr ==2.6.1.2 +python3.8

• 运行指令/Command Code：
  python执行以下脚本：
  import cv2
  from paddleocr import PPStructure,save_structure_res,PaddleOCR
  table_engine = PPStructure(layout=False, show_log=True)
  img = cv2.imread("./5_0.jpg") #OOM
  result = table_engine(img)
  print(result)

• 完整报错/Complete Error Message：
  /home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddle/vision/transforms/functional_pil.py:36: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.
  'nearest': Image.NEAREST,
  /home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddle/vision/transforms/functional_pil.py:37: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
  'bilinear': Image.BILINEAR,
  /home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddle/vision/transforms/functional_pil.py:38: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
  'bicubic': Image.BICUBIC,
  /home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddle/vision/transforms/functional_pil.py:39: DeprecationWarning: BOX is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BOX instead.
  'box': Image.BOX,
  /home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddle/vision/transforms/functional_pil.py:40: DeprecationWarning: LANCZOS is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.LANCZOS instead.
  'lanczos': Image.LANCZOS,
  /home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddle/vision/transforms/functional_pil.py:41: DeprecationWarning: HAMMING is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.HAMMING instead.
  'hamming': Image.HAMMING
  [2023/01/04 11:26:44] ppocr DEBUG: Namespace(alpha=1.0, benchmark=False, beta=1.0, cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir=None, cls_thresh=0.9, cpu_threads=10, crop_res_save_dir='./output', det=True, det_algorithm='DB', det_box_type='quad', det_db_box_thresh=0.6, det_db_score_mode='fast', det_db_thresh=0.3, det_db_unclip_ratio=1.5, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_east_score_thresh=0.8, det_limit_side_len=960, det_limit_type='max', det_model_dir='/home/ubuntu/.paddleocr/whl/det/ch/ch_PP-OCRv3_det_infer', det_pse_box_thresh=0.85, det_pse_min_area=16, det_pse_scale=1, det_pse_thresh=0, det_sast_nms_thresh=0.2, det_sast_score_thresh=0.5, draw_img_save_dir='./inference_results', drop_score=0.5, e2e_algorithm='PGNet', e2e_char_dict_path='./ppocr/utils/ic15_dict.txt', e2e_limit_side_len=768, e2e_limit_type='max', e2e_model_dir=None, e2e_pgnet_mode='fast', e2e_pgnet_score_thresh=0.5, e2e_pgnet_valid_set='totaltext', enable_mkldnn=False, fourier_degree=5, gpu_mem=500, help='==SUPPRESS==', image_dir=None, image_orientation=False, ir_optim=True, kie_algorithm='LayoutXLM', label_list=['0', '180'], lang='ch', layout=False, layout_dict_path='/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/ppocr/utils/dict/layout_dict/layout_cdla_dict.txt', layout_model_dir='/home/ubuntu/.paddleocr/whl/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer', layout_nms_threshold=0.5, layout_score_threshold=0.5, max_batch_size=10, max_text_length=25, merge_no_span_structure=True, min_subgraph_size=15, mode='structure', ocr=True, ocr_order_method=None, ocr_version='PP-OCRv3', output='./output', page_num=0, precision='fp32', process_id=0, re_model_dir=None, rec=True, rec_algorithm='SVTR_LCNet', rec_batch_num=6, rec_char_dict_path='/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/ppocr/utils/ppocr_keys_v1.txt', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_model_dir='/home/ubuntu/.paddleocr/whl/rec/ch/ch_PP-OCRv3_rec_infer', recovery=False, save_crop_res=False, save_log_path='./log_output/', scales=[8, 16, 32], ser_dict_path='../train_data/XFUND/class_list_xfun.txt', ser_model_dir=None, show_log=True, sr_batch_num=1, sr_image_shape='3, 32, 128', sr_model_dir=None, structure_version='PP-StructureV2', table=True, table_algorithm='TableAttn', table_char_dict_path='/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/ppocr/utils/dict/table_structure_dict_ch.txt', table_max_len=488, table_model_dir='/home/ubuntu/.paddleocr/whl/table/ch_ppstructure_mobile_v2.0_SLANet_infer', total_process_num=1, type='ocr', use_angle_cls=False, use_dilation=False, use_gpu=True, use_mp=False, use_npu=False, use_onnx=False, use_pdf2docx_api=False, use_pdserving=False, use_space_char=True, use_tensorrt=False, use_visual_backbone=True, use_xpu=False, vis_font_path='./doc/fonts/simfang.ttf', warmup=False)
  [2023/01/04 11:26:44] ppocr WARNING: When args.layout is false, args.ocr is automatically set to false
  [2023/01/04 11:26:47] ppocr DEBUG: dt_boxes num : 25, elapse : 0.027103662490844727
  Traceback (most recent call last):
  File "test_paddle.py", line 6, in
  result = table_engine(img)
  File "/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/paddleocr.py", line 645, in call
  res, _ = super().call(
  File "/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/ppstructure/predict_system.py", line 129, in call
  res, table_time_dict = self.table_system(
  File "/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/ppstructure/table/predict_table.py", line 90, in call
  dt_boxes, rec_res, det_elapse, rec_elapse = self._ocr(
  File "/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/ppstructure/table/predict_table.py", line 137, in _ocr
  rec_res, rec_elapse = self.text_recognizer(img_crop_list)
  File "/home/ubuntu/project/lib20221230/env38/lib/python3.8/site-packages/paddleocr/tools/infer/predict_rec.py", line 608, in call
  self.predictor.run()
  RuntimeError: ResourceExhaustedError:

Out of memory error on GPU 0. Cannot allocate 8.254151GB memory on GPU 0, 5.149536GB memory has been allocated and available memory is only 6.752441GB.

Please check whether there is any other process using GPU 0.

1. If yes, please stop them, or start PaddlePaddle on another GPU.
2. If no, please decrease the batch size of your model.

(at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79)

大部分图片识别时只需要1G多显存就可以正常识别，但是个别图片就会要求分配8.254151GB的显存导致OOM

[tink2123]

当表格中存在的单元格过多时，可能会导致显存占用过大。

[danbao12138]

当表格中存在的单元格过多时，可能会导致显存占用过大。

1，图片中并没有过多的单元格，许多可以正常识别的图片包含的单元格要比这几张导致OOM的单于格多的多。
2，当我清理出8G多的显存来跑这些个别的图片的时候，输出并没有什么不同，检测出的单于格也是正常的。
3，我的图片大部分都是50K左右，大小都在（631, 338）左右
4，甚至，我将这些导致OOM的图片去掉一行像素，或者进行简单裁剪都能过正常识别，但是这不能根本上解决问题，因为并不知道哪些图片需要裁剪。

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.