process hangs when invoking ocr function in Apple M1 Max

[felixgao]

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：Mac M1 Max
• 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：
• 完整报错/Complete Error Message：

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.

❯ python ocr.py
[2023/09/06 16:14:12] 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, gpu_id=0, image_dir=None, page_num=0, det_algorithm='DB', det_model_dir='/Users/ggao/.paddleocr/whl/det/en/en_PP-OCRv3_det_infer', det_limit_side_len=960, 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='fast', 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='/Users/ggao/.paddleocr/whl/rec/en/en_PP-OCRv4_rec_infer', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='/Users/ggao/experiments/extraction/.venv/lib/python3.10/site-packages/paddleocr/ppocr/utils/en_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=True, cls_model_dir='/Users/ggao/.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, return_word_box=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', image_orientation=False, layout=True, table=True, ocr=True, recovery=False, use_pdf2docx_api=False, lang='en', det=True, rec=True, type='ocr', ocr_version='PP-OCRv4', structure_version='PP-StructureV2')
[1]    72471 killed     python ocr.py

I have to kill the process after more than 20 seconds of 100% process CPU utilization.

the code is simple

from paddleocr import PaddleOCR
p = PaddleOCR(use_angle_cls=True, lang="en")   
r = p.ocr("/Users/ggao/Downloads/ocr_image.png")
pp.pprint(r) 

[felixgao]

Had to force kill the process.

[lookou]

i got the same problem, too.

[a1d4r]

Same problem on M1 Pro

[pranay-009]

same problem on M2

[a1d4r]

Tried to build a docker image with --platform=linux/amd64 and run it with Rosetta. No success :(

[MariusMez]

Same issue with latest install on MBP M1 Max

[dgarnitz]

Same problem. anyone solve it yet?

[ixiami1314]

同样的问题！如果用intel芯片的苹果是可以的，但又换成另外一个问题了，在执行手工标注任务时，系统又会闪退。

[SWHL]

Please try to update the Paddle version to the latest, and use the latest code of PaddleOCR.
When install the paddle, you may need to verify whether paddle is installed successfully. You can try to run the following:

import paddle

paddle.utils.run_check()
#  Appear Successfully  → ✔

[BloodLine888]

Still an issue, it is frozen after execution on

Apple M1 Max | OS Sonoma 14.4|Python 3.11.7 64Bit

• pip (M1 ❌)

 python -m pip install paddlepaddle==2.6.1 -i https://mirror.baidu.com/pypi/simple

• conda (M1 ❌)

conda update -n base -c defaults conda
conda create -n paddle_ocr_env python=3.11
conda activate paddle_ocr_env
conda install paddlepaddle==2.6.1 --channel https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/

Code

from paddleocr import PaddleOCR
import paddle
import os

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

#########################################################################################
paddle.utils.run_check()

def main():
    try:
        ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False, show_log=True)
        result = ocr.ocr(img_path, cls=True)
        print(result)
    except Exception as e:
        print(e)

if __name__ == '__main__':
    main()

Output

Running verify PaddlePaddle program ...
I0611 20:12:02.341153 69712576 program_interpreter.cc:212] New Executor is Running.
I0611 20:12:02.379716 69712576 interpreter_util.cc:624] Standalone Executor is Used.
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0611 20:12:02.381100 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381175 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381237 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381242 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381255 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381258 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381274 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381314 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381320 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381335 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381338 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381340 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381351 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381354 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381356 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381477 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381525 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381548 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381572 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381585 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381611 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381635 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381650 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381666 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381687 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381690 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381692 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381695 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381696 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381700 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381700 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381724 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381728 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381729 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381732 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381734 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381736 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
I0611 20:12:02.381737 69712576 kernel_dispatch.h:102] Get BackendSet from tensor
PaddlePaddle works well on 1 CPU.
PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.
[2024/06/11 20:12:02] 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, gpu_id=0, image_dir=None, page_num=0, det_algorithm='DB', det_model_dir='/Users/USER/.paddleocr/whl/det/en/en_PP-OCRv3_det_infer', det_limit_side_len=960, 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='fast', 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='/Users/USER/.paddleocr/whl/rec/en/en_PP-OCRv4_rec_infer', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='/opt/homebrew/lib/python3.11/site-packages/paddleocr/ppocr/utils/en_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=True, cls_model_dir='/Users/USER/.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', image_orientation=False, layout=True, table=True, ocr=True, recovery=False, use_pdf2docx_api=False, invert=False, binarize=False, alphacolor=(255, 255, 255), lang='en', det=True, rec=True, type='ocr', ocr_version='PP-OCRv4', structure_version='PP-StructureV2')

<---and it is frozen at this point (no error)

[SWHL]

I seem to find the reason. Please run the following code to check the platform:

$ python -m platform

# if show macOS-14.5-arm64-arm-64bit → ✔
# if show macOS-10.16-x86_64-i386-64bit → ✗

If your python is macOS-10.16-x86_64-i386-64bit, you could try to install the arm version conda. You can refer this link, and after this, try again.

[GreatV]

@BloodLine888 Try installing the PaddlePaddle development version from https://www.paddlepaddle.org.cn/en/install/quick

[BloodLine888]

I tried from docs using pip and same result, it is frozen after execution

• python -m platform > macOS-14.5-arm64-arm-64bit

• python3 -m pip install paddlepaddle==2.6.0 -i https://mirror.baidu.com/pypi/simple

• python3 -m pip install paddleocr > paddleocr-2.7.3

• python3 -m pip --version > pip 24.0 ...3.10.10/lib/python3.10/site-packages/pip (python 3.10)

python3 main.py

Code

from paddleocr import PaddleOCR
import os

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

#########################################################################################
img_path = '/Users/USER/Desktop/PaddleOCR/examples/small_screen_559_154.png'

def main():
    try:
        ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False, show_log=True)
        result = ocr.ocr(img_path, cls=True)
        print(result)
    except Exception as e:
        print(e)

if __name__ == '__main__':
    main()

output

python3 main.py
[2024/06/13 19:46:39] 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, gpu_id=0, image_dir=None, page_num=0, det_algorithm='DB', det_model_dir='/Users/USER/.paddleocr/whl/det/en/en_PP-OCRv3_det_infer', det_limit_side_len=960, 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='fast', 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='/Users/USER/.paddleocr/whl/rec/en/en_PP-OCRv4_rec_infer', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='/Users/USER/.pyenv/versions/3.10.10/lib/python3.10/site-packages/paddleocr/ppocr/utils/en_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=True, cls_model_dir='/Users/USER/.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', image_orientation=False, layout=True, table=True, ocr=True, recovery=False, use_pdf2docx_api=False, invert=False, binarize=False, alphacolor=(255, 255, 255), lang='en', det=True, rec=True, type='ocr', ocr_version='PP-OCRv4', structure_version='PP-StructureV2')

[GreatV]

@BloodLine888 Did you install the development version of PaddlePaddle from this link https://www.paddlepaddle.org.cn/en/install/quick and try again?

[BloodLine888]

ah, development build, sorry I missed that part, yes, then it works!
python -m pip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/mac/cpu/develop.html

thank you!