set `use_gpu=True` but the debugging log shows `use_gpu=False`

[annahung31]

Hi 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]

Check if the log output is before updating useugpu=true. During the training process, it is possible to check if the GPU memory has changed to determine whether the GPU has been used.

[annahung31]

Thanks for replying. I use the check_gpu function to test directly and still found the result is False. It turns out that I didn't set up the paddlepaddle-gpu correctly so it cannot access to my GPU.

The reason is that the Cuda version is not aligned with my environment.

So instead of installing paddlepaddle-gpu via pip, I turned to use the docker image with the correct cuda version, and then it worked.

[omumarvaishya005]

hii guys im also having the same issue even i have fixed use_gpu as true but when im debugging its saying use_gpu=false here is the debug message please help me i need a urgent support ppocr DEBUG: Namespace(help='==SUPPRESS==', use_gpu=False, use_xpu=False, use_npu=False, ir_optim=True, use_tensorrt=False, min_subgraph_size=15, precision='fp32', gpu_mem=500, image_dir=None, page_num=0, det_algorithm='DB', det_model_dir='/var/www/ocr/models/det/v2/inference/', det_limit_side_len=2000, det_limit_type='max', det_box_type='quad', det_db_thresh=0.3, det_db_box_thresh=0.6, det_db_unclip_ratio=1.5, max_batch_size=10, use_dilation=False, det_db_score_mode='slow', det_east_score_thresh=0.8, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_sast_score_thresh=0.5, det_sast_nms_thresh=0.2, det_pse_thresh=0, det_pse_box_thresh=0.85, det_pse_min_area=16, det_pse_scale=1, scales=[8, 16, 32], alpha=1.0, beta=1.0, fourier_degree=5, rec_algorithm='SVTR_LCNet', rec_model_dir='/var/www/ocr/models/rec/v3/inference/', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='/var/www/ocr/models/rec/v3/inference/dict.txt', use_space_char=True, vis_font_path='./doc/fonts/simfang.ttf', drop_score=0.5, e2e_algorithm='PGNet', e2e_model_dir=None, e2e_limit_side_len=768, e2e_limit_type='max', e2e_pgnet_score_thresh=0.5, e2e_char_dict_path='./ppocr/utils/ic15_dict.txt', e2e_pgnet_valid_set='totaltext', e2e_pgnet_mode='fast', use_angle_cls=False, cls_model_dir='/home/astc/.paddleocr/whl/cls/ch_ppocr_mobile_v2.0_cls_infer', cls_image_shape='3, 48, 192', label_list=['0', '180'], cls_batch_num=6, cls_thresh=0.9, enable_mkldnn=False, cpu_threads=10, use_pdserving=False, warmup=False, sr_model_dir=None, sr_image_shape='3, 32, 128', sr_batch_num=1, draw_img_save_dir='./inference_results', save_crop_res=False, crop_res_save_dir='./output', use_mp=False, total_process_num=1, process_id=0, benchmark=False, save_log_path='./log_output/', show_log=True, use_onnx=False, output='./output', table_max_len=488, table_algorithm='TableAttn', table_model_dir=None, merge_no_span_structure=True, table_char_dict_path=None, layout_model_dir=None, layout_dict_path=None, layout_score_threshold=0.5, layout_nms_threshold=0.5, kie_algorithm='LayoutXLM', ser_model_dir=None, re_model_dir=None, use_visual_backbone=True, ser_dict_path='../train_data/XFUND/class_list_xfun.txt', ocr_order_method=None, mode='structure', imag

[UserWangZz]

hii guys im also having the same issue even i have fixed use_gpu as true but when im debugging its saying use_gpu=false here is the debug message please help me i need a urgent support

This may be a bug. You can track use_gpu to see if the parameters passed in are normal, update the default configuration, and make sure the paddle version is paddlepaddle-gpu.

[omumarvaishya005]

thanks for replying can we connect to solve the issue as im in urgent need for this , it would be very helpful for me

[UserWangZz]

Check whether the gpu memory of the model inference process changes after setting use_gpu=True, because this may be just a small problem with the logger.

[omumarvaishya005]

yes i checked it earlier when im trying to run inference it is more using gpu anymore even in log file use_gpu ismarked as false please help me regarding this

[UserWangZz]

When executing inference, is there any obvious change in the GPU memory?

[omumarvaishya005]

no there is no significant chnage in gpu usages its only using cpu

[omumarvaishya005]

hii @UserWangZz can we connect over a quick call to solve the issue??

[UserWangZz]

hii @UserWangZz can we connect over a quick call to solve the issue?? Of course

[omumarvaishya005]

okay can we do it now?? https://meet.google.com/tse-uxbw-hvx this is link here you can join

[UserWangZz]

okay can we do it now?? https://meet.google.com/tse-uxbw-hvx this is link here you can join

sorry, i miss this message

[omumarvaishya005]

so please give me time when you can join it and make sure it is arabic time zone since im in saudi arabia thanks for being kind and help full

[UserWangZz]

so please give me time when you can join it and make sure it is arabic time zone since im in saudi arabia thanks for being kind and help full

sorry, can you provide your code for me？ and your environment about paddlepaddle and Paddleocr etc. I will try to reproduce your problem

[omumarvaishya005]

if you can join then we can solve the issue very quickly other wise we both will be wasting our time

[omumarvaishya005]

requirements.txt this is the requirment file that im using

[omumarvaishya005]

since its a big project so sharing every thing will be not be easy

[omumarvaishya005]

@UserWangZz i think i don't have paddle-gpu module with my requirement file that's why this issue is coming

[omumarvaishya005]

Yes yes that's was the issue thank you so much for your support 🙏 i appreciate you kind help