PaddleOCR 运行报错。FatalError: Illegal instruction is detected by the operating system.（非常着急）

[linqunbin]

• 系统环境/System Environment：Operating System: Ubuntu 22.04.4 LTS，Kernel: Linux 6.5.0-21-generic， Architecture: x86-64
• 版本号/Version：
• Paddle ： 2.6.0
• PaddleOCR： 2.7.0.3

我的电脑是CPU的环境，网上搜索了很多材料都没有找到相关解决办法，通过运行如下：
import paddle

paddle.utils.run_check()

PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.

可以看到 PaddlePaddle 已经安装成功了，但 PaddleOCR 跑步起来就报错：

from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR(use_angle_cls=True, lang="ch")

运行以上代码，报错信息如下：

Error Message Summary:
FatalError: Illegal instruction is detected by the operating system.
[TimeInfo: *** Aborted at 1709025734 (unix time) try "date -d @1709025734" if you are using GNU date ***]
[SignalInfo: *** SIGILL (@0x7f278b41e86a) received by PID 44052 (TID 0x7f2792799000) from PID 18446744071750936682 ***]

另外，使用：cat /proc/cpuinfo | grep avx2，可以看出我的电脑是支持该指令的。

[jzhang533]

cc: @michaelowenliu

[TingquanGao]

建议使用openvino后端试试

[leavor]

一模一样

paddleocr 2.7.0.3
paddlepaddle 2.6.1

C++ Traceback (most recent call last):

0 paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&)
1 std::unique_ptr<paddle::PaddlePredictor, std::default_deletepaddle::PaddlePredictor > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
2 paddle::AnalysisPredictor::Init(std::shared_ptrpaddle::framework::Scope const&, std::shared_ptrpaddle::framework::ProgramDesc const&)
3 paddle::AnalysisPredictor::PrepareProgram(std::shared_ptrpaddle::framework::ProgramDesc const&)
4 paddle::AnalysisPredictor::OptimizeInferenceProgram()
5 paddle::inference::analysis::Analyzer::RunAnalysis(paddle::inference::analysis::Argument*)
6 paddle::inference::analysis::IrAnalysisPass::RunImpl(paddle::inference::analysis::Argument*)
7 paddle::inference::analysis::IRPassManager::Apply(std::unique_ptr<paddle::framework::ir::Graph, std::default_deletepaddle::framework::ir::Graph >)
8 paddle::framework::ir::Pass::Apply(paddle::framework::ir::Graph*) const
9 paddle::framework::ir::SelfAttentionFusePass::ApplyImpl(paddle::framework::ir::Graph*) const
10 paddle::framework::ir::GraphPatternDetector::operator()(paddle::framework::ir::Graph*, std::function<void (std::map<paddle::framework::ir::PDNode*, paddle::framework::ir::Node*, paddle::framework::ir::GraphPatternDetector::PDNodeCompare, std::allocator<std::pair<paddle::framework::ir::PDNode* const, paddle::framework::ir::Node*> > > const&, paddle::framework::ir::Graph*)>)

---

Error Message Summary:

FatalError: Illegal instruction is detected by the operating system.
[TimeInfo: *** Aborted at 1711072502 (unix time) try "date -d @1711072502" if you are using GNU date ***]
[SignalInfo: *** SIGILL (@0x7fddeb44c13a) received by PID 1607 (TID 0x7fde2343f740) from PID 18446744073361735994 ***]

/tmp/tmp7h6uav3o: 行 3: 1607 非法指令 (吐核)python /home/leavor/project/llm_ocr/ocr.py
ERROR conda.cli.main_run:execute(124): conda run python /home/leavor/project/llm_ocr/ocr.py failed. (See above for error)

[leavor]

I downgraded the version of paddlepaddle to 2.5.2 and the issue was solved

降低 paddlepaddle的版本到2.5.2，问题解决

[loli0123456789]

按照这个办法搞定了，thanks。

[jacky8899]

一毛一样, ubuntu ,proxmox
cat /proc/cpuinfo | grep -i avx 显示 支持 avx2
用docker版本能够运行，但用http。。。(https://hub.docker.com/r/duolabmeng666/paddlehub_ppocr)
用官方paddle docker2.6.1再安装paddleocr，执行也是下面的错误

paddleocr --image_dir ./testocr.png
[2024/03/29 15:26:15] 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='./testocr.png', page_num=0, det_algorithm='DB', det_model_dir='/root/.paddleocr/whl/det/ch/ch_PP-OCRv4_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='/root/.paddleocr/whl/rec/ch/ch_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='/root/.pyenv/versions/3.12.2/lib/python3.12/site-packages/paddleocr/ppocr/utils/ppocr_keys_v1.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='/root/.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='ch', det=True, rec=True, type='ocr', ocr_version='PP-OCRv4', structure_version='PP-StructureV2')

---

C++ Traceback (most recent call last):

0 paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&)
1 std::unique_ptr<paddle::PaddlePredictor, std::default_deletepaddle::PaddlePredictor > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
2 paddle::AnalysisPredictor::Init(std::shared_ptrpaddle::framework::Scope const&, std::shared_ptrpaddle::framework::ProgramDesc const&)
3 paddle::AnalysisPredictor::PrepareProgram(std::shared_ptrpaddle::framework::ProgramDesc const&)
4 paddle::AnalysisPredictor::OptimizeInferenceProgram()
5 paddle::inference::analysis::Analyzer::RunAnalysis(paddle::inference::analysis::Argument*)
6 paddle::inference::analysis::IrAnalysisPass::RunImpl(paddle::inference::analysis::Argument*)
7 paddle::inference::analysis::IRPassManager::Apply(std::unique_ptr<paddle::framework::ir::Graph, std::default_deletepaddle::framework::ir::Graph >)
8 paddle::framework::ir::Pass::Apply(paddle::framework::ir::Graph*) const
9 paddle::framework::ir::SelfAttentionFusePass::ApplyImpl(paddle::framework::ir::Graph*) const
10 paddle::framework::ir::GraphPatternDetector::operator()(paddle::framework::ir::Graph*, std::function<void (std::map<paddle::framework::ir::PDNode*, paddle::framework::ir::Node*, paddle::framework::ir::GraphPatternDetector::PDNodeCompare, std::allocator<std::pair<paddle::framework::ir::PDNode* const, paddle::framework::ir::Node*> > > const&, paddle::framework::ir::Graph*)>)

---

Error Message Summary:

FatalError: Illegal instruction is detected by the operating system.
[TimeInfo: *** Aborted at 1711697176 (unix time) try "date -d @1711697176" if you are using GNU date ***]
[SignalInfo: *** SIGILL (@0x7f40c53cb9ba) received by PID 44095 (TID 0x7f40cbe36740) from PID 18446744072723675578 ***]

[jacky8899]

解决了，要用python3.7，并且proxmox的vm要直通cpu(host).参考这个
https://github.com/PaddlePaddle/PaddleOCR/blob/4865410ebb4bb215cd550fce5da99c3d3af348d0/deploy/docker/hubserving/cpu/Dockerfile

[yooyo-Q]

I downgraded the version of paddlepaddle to 2.5.2 and the issue was solved

降低 paddlepaddle的版本到2.5.2，问题解决

1.实体机亲测可以解决，2.虚拟机在跑demo文件时，如果使用for循环ocr.ocr识别完成后貌似不会释放内存，连续识别图像，前几张可以，后几张报错“Process finished with exit code 137 (interrupted by signal 9:SIGKILL)”。 内存不足杀进程了

[miss85246]

实测发现在多台机器上，如果是在虚拟环境中， 则会复现该错误， 如果不在虚拟环境中，就可以正常执行

[jwsky]

按照这里的说明，用最新版后，问题修复成功了
#13327

pip install paddlepaddle==3.0.0b2 --upgrade