(External) CUBLAS error(7)

[shiyutang]

• 系统环境/System Environment：centos7
• 版本号/Version：Paddle：2.5.1 PaddleOCR：2.7.0.2 问题相关组件/Related components：
• 运行指令/Command Code： paddleocr --image_dir word_1.jpg --lang=ch
• CUDA： cuda 10.2
• 完整报错/Complete Error Message： [2023/08/28 16:53:26] ppocr DEBUG: Namespace(alpha=1.0, benchmark=False, beta=1.0, cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir='/root/.paddleocr/whl/cls/ch_ppocr_mobile_v2.0_cls_infer', 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='/root/.paddleocr/whl/det/ch/ch_PP-OCRv4_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_id=0, gpu_mem=500, help='==SUPPRESS==', image_dir='/opt/ai/liucong/Project/video-to-text-ocr/ppocr_img/ch/word_1.jpg', image_orientation=False, ir_optim=True, kie_algorithm='LayoutXLM', label_list=['0', '180'], lang='ch', layout=True, layout_dict_path=None, layout_model_dir=None, 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-OCRv4', 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/zg/anaconda-zg/anaconda3/envs/py38/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='/root/.paddleocr/whl/rec/ch/ch_PP-OCRv4_rec_infer', recovery=False, return_word_box=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=None, table_max_len=488, table_model_dir=None, 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)

[2023/08/28 16:53:29] ppocr INFO: **/opt/ai/ppocr_img/ch/word_1.jpg** [2023/08/28 16:53:30] ppocr DEBUG: dt_boxes num : 31, elapse : 0.8258509635925293

Traceback (most recent call last): File "/home/zg/anaconda-zg/anaconda3/envs/py38/bin/paddleocr", line 8, in sys.exit(main()) File "/home/zg/anaconda-zg/anaconda3/envs/py38/lib/python3.8/site-packages/paddleocr/paddleocr.py", line 766, in main result = engine.ocr(img_path, File "/home/zg/anaconda-zg/anaconda3/envs/py38/lib/python3.8/site-packages/paddleocr/paddleocr.py", line 648, in ocr dt_boxes, recres, = self.call(img, cls) File "/home/zg/anaconda-zg/anaconda3/envs/py38/lib/python3.8/site-packages/paddleocr/tools/infer/predict_system.py", line 95, in call rec_res, elapse = self.text_recognizer(img_crop_list) File "/home/zg/anaconda-zg/anaconda3/envs/py38/lib/python3.8/site-packages/paddleocr/tools/infer/predict_rec.py", line 619, in call self.predictor.run() OSError: (External) CUBLAS error(7). [Hint: 'CUBLAS_STATUS_INVALID_VALUE'. An unsupported value or parameter was passed to the function (a negative vector size, for example). To correct: ensure that all the parameters being passed have valid values. ] (at ../paddle/phi/backends/gpu/gpu_context.cc:599) [operator < fc > error]

我们提供了AceIssueSolver来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no):yes

请尽量不要包含图片在问题中/Please try to not include the image in the issue.

[aceissuesolver[bot]]

Issue Response

• ✨ Introduction: Thanks for opening this issue, I am the AceIssueSolver that will help you with your questoins!
• 🎯 First round response: The answer to your question is:

根据报错信息，您遇到了一个与CUBLAS相关的错误。这个错误提示表明在函数中传递了一个不支持的值或参数，导致了CUBLAS错误。

为了解决这个问题，您可以尝试以下步骤：

1. 检查兼容性：确保PaddleOCR、PaddlePaddle和CUDA的版本相互兼容。在您的情况下，您正在使用PaddleOCR 2.7.0.2和CUDA 10.2。验证这些版本是否兼容。

2. 检查输入图片：确保输入图片的格式正确，并且可以被PaddleOCR正确读取。您可以尝试使用OpenCV（cv2.imread()）打开图片，以验证是否可以成功读取。

3. 检查运行指令：仔细检查您用来运行PaddleOCR的指令代码。确保所有参数都是正确和有效的。在您的情况下，指令代码是 paddleocr --image_dir word_1.jpg --lang=ch。确保 image_dir 参数指向正确的图片文件。

4. 检查GPU内存：验证您是否有足够的GPU内存来运行PaddleOCR。指令代码中的 gpu_mem 参数指定要使用的GPU内存量。如果内存不足，可以尝试减小这个值。

如果在尝试了这些步骤之后问题仍然存在，提供更多关于您的系统环境的信息可能会有助于进一步诊断问题，例如PaddleOCR、PaddlePaddle和CUDA的版本，以及其他相关细节。这将有助于进一步解决问题。

How to use

To invoke the AceIssueSolver, add a comment using one of the following commands: @Ace-issue-solver \<QUESTION>: Pose more questions on AceIssueSolver.