PaddlePaddle / PaddlePaddle/FastDeploy

fd.vision.ocr.PPOCRv3初始化模型后调用predict(im)无返回,报错:Process finished with exit code -1073741819 (0xC0000005)

Open
#2,496 1 comment 0 reactions 1 assignee View on GitHub

@rainyfly is already working on this.

Since Jul 18, 2024.

Dominant language
Python
Stars
3.7k
Forks
756
Avg merge
19h 28m
Merged PRs (30d)
4

Description


温馨提示:根据社区不完全统计,按照模板提问,可以加快回复和解决问题的速度


环境

  • 【FastDeploy版本】:fastdeploy-python-1.0.7
  • 【编译命令】如果您是自行编译的FastDeploy,请说明您的编译方式(参数命令)
  • 【系统平台】: Windows x64(Windows10)
  • 【硬件】: CPU
  • 【编译语言】:Python(3.8)

问题日志及出现问题的操作流程

  • 【模型跑不通】
  • 问题说明:fd.vision.ocr.PPOCRv3(det_model=build_det_model(), rec_model=build_rec_model());初始化模型后调用predict(im)无返回
  • 报错:Process finished with exit code -1073741819 (0xC0000005)
    下面是我的代码:

import fastdeploy as fd
import cv2
import os
def build_det_model():
    det_model_file = "./model/det_db_inference/inference.pdmodel"
    det_params_file = "./model/det_db_inference/inference.pdiparams"
    # Set the runtime option
    det_option = fd.RuntimeOption()
    det_option.use_cpu()
    # det_option.use_openvino_backend()

    # Create the det_model
    det_model = fd.vision.ocr.DBDetector(
        det_model_file, det_params_file, runtime_option=det_option)

    # Set the preporcessing parameters
    det_model.preprocessor.max_side_len = 960
    det_model.postprocessor.det_db_thresh = 0.3
    det_model.postprocessor.det_db_box_thresh = 0.6
    det_model.postprocessor.det_db_unclip_ratio = 1.5
    det_model.postprocessor.det_db_score_mode = "slow"
    det_model.postprocessor.use_dilation = False
    return det_model


def build_rec_model():
    rec_model_file = "./model/rec_ppocr_v3_distillation/Teacher/inference.pdmodel"
    rec_params_file = "./model/rec_ppocr_v3_distillation/Teacher/inference.pdiparams"
    rec_label_file = "./model/rec_ppocr_v3_distillation/lesson_letter.txt"
    # Set the runtime option
    rec_option = fd.RuntimeOption()
    rec_option.use_cpu()
    # rec_option.use_openvino_backend()

    rec_model = fd.vision.ocr.Recognizer(
        rec_model_file, rec_params_file, rec_label_file, runtime_option=rec_option)
    rec_model.rec_image_shape = [3, 48, 48]
    return rec_model


if __name__ == '__main__':
    im = cv2.imread("./imgs/19.png")
    ppocr_v3 = fd.vision.ocr.PPOCRv3(det_model=build_det_model(), rec_model=build_rec_model())
    result = ppocr_v3.predict(im)
    print(result)

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.