【急问】PaddleOCR对单张图片做文字识别，设置use_gpu=True的情况下出结果要大致15秒。这个速度是正常的吗？

[tiesanguaixia]

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

【没有报错】

• 系统环境/System Environment：CUDA 11
• 版本号/Version：Paddle：paddlepaddle==2.5.2 PaddleOCR：2.7.2 问题相关组件/Related components：
• 运行指令/Command Code：
• 完整报错/Complete Error Message：

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

1. PaddleOCR(use_angle_cls=False, lang="ch", use_gpu=True) 运行时GPU显存占用一直都是0，是不是没有成功调用GPU呢？
2. 目前推理速度比较慢，猜测一方面是GPU没用起来？另一方面如果只做文字识别，不做别的任务代码应该是什么样子呢，出结果会不会更快一点？

期待您的解答，感激不尽！

[cuicheng01]

1. 您的GPU类型是什么呢？
2. 您在使用的过程中，可以打印一下不同模块的耗时，如前处理时间，后处理时间，infer时间，前后处理依赖于CPU，如果CPU性能不好，也会影响最终的性能。 结论：15秒不正常，建议按照1和2再查一下哈

[tink2123]

gpu利用率为0，应该是没有使用GPU。 是否安装了gpu版本的paddle呢

[annahung31]

hi, I'm facing the same issue. I set use_gpu=True but the debugging log shows use_gpu=False.... What should I do?

The following is my env setting:

paddlepaddle-gpu 2.5.0
paddlepaddle 2.6.1
paddleocr 2.7.2
cuda version  10.8

my code:

    ocr = PaddleOCR(use_angle_cls=True, 
                    use_gpu=True,
                    lang="ch")

debugging message:

[2024/04/12 03:27:49] ppocr DEBUG: Namespace(alpha=1.0, alphacolor=(255, 255, 255), benchmark=False, beta=1.0, binarize=False, cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir='/root/.paddleocr/whl/cls/ch/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/en/ch_PP-OCRv4_det_server_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=None, image_orientation=False, invert=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='/usr/local/lib/python3.8/dist-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/en/ch_PP-OCRv4_rec_server_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=None, table_max_len=488, table_model_dir=None, total_process_num=1, type='ocr', use_angle_cls=True, use_dilation=False, use_gpu=False, 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) [2024/04/12 03:27:54] ppocr DEBUG: dt_boxes num : 49, elapsed : 3.9109363555908203 [2024/04/12 03:27:55] ppocr DEBUG: cls num : 49, elapsed : 0.08451628684997559 [2024/04/12 03:28:05] ppocr DEBUG: rec_res num : 49, elapsed : 10.290374040603638

inference time: 15.56s

[UserWangZz]

paddlepaddle-gpu 2.5.0 paddlepaddle 2.6.1 paddleocr 2.7.2 cuda version 10.8 you install the paddlepaddle and paddlepaddle-gpu. you should uninstall paddlepaddle 2.6.1, and check it again