paddleocr 打包为web服务

作者: LCSan | 来源:发表于2021-04-08 22:42 被阅读0次

paddleocr 打包为web服务
5、持续集成-jenkins
如何将Spring Boot项目部署为Windows服务，并设置
第二十六节、运维脚本编写实例
linux挂载windows服务器某个文件夹
Linux运维-day36-综合架构-rsync全网备份
rsync全网备份服务
maven——jar和war的区别
产品前端架构 1-3
2021-05-25 使用nodejs搭建web服务器&flut

依赖库，保存为requirements.txt

altgraph==0.17
astor==0.8.1
chardet==3.0.4
click==7.1.2
cycler==0.10.0
decorator==4.4.2
funcsigs==1.0.2
future==0.18.2
gast==0.3.3
graphviz==0.14.2
idna==2.10
imageio==2.9.0
imgaug==0.4.0
joblib==0.17.0
kiwisolver==1.2.0
lmdb==1.0.0
matplotlib==3.3.2
networkx==2.5
nltk==3.5
np-utils==0.5.12.1
numpy==1.19.2
objgraph==3.4.1
opencv-python==4.2.0.32
paddleocr==1.0.0
paddlepaddle==1.8.5
pathlib==1.0.1
pefile==2019.4.18
Pillow==7.1.2
prettytable==1.0.1
protobuf==3.13.0
py-notifier==0.1.0
pyclipper==1.2.0
pyinstaller==4.0
pyinstaller-hooks-contrib==2020.9
pyparsing==2.4.7
pyperclip==1.8.0
pypiwin32==223
PyQt5==5.14.2
PyQt5-sip==12.7.2
pytesseract==0.3.4
python-dateutil==2.8.1
PyWavelets==1.1.1
pywin32==228
pywin32-ctypes==0.2.0
PyYAML==5.3.1
rarfile==4.0
regex==2020.10.11
requests==2.24.0
scikit-image==0.17.2
scipy==1.5.2
six==1.15.0
system-hotkey==1.0.3
tifffile==2020.10.1
tqdm==4.50.2
urllib3==1.25.10
wcwidth==0.2.5
wincertstore==0.2
flask==1.1.2

conda构建虚拟环境

conda create -n pppocr python=3.7
conda activate pppocr
cd %~dp0
%~d0
pip install -r requirements.txt

3.打包主文件ocr.py

#!/usr/bin/env python
# coding=utf-8
# 文件上传服务器端,只考虑文件在当前目录下
from paddleocr import PaddleOCR
from os.path import join, dirname, exists, splitext
from flask import Flask, request
import os
import uuid
from configparser import ConfigParser
import re

# web服务
app = Flask(__name__)
# paddlerocr对象
pocr = None
# 配置文件
config = {}

def init():
    global pocr
    global config
    conf = ConfigParser()
    confpath = os.path.join(os.getcwd(), "config.ini")
    conf.read(confpath, encoding="utf-8-sig")
    for sec in conf.sections():
        temp = dict(conf[sec])
        for item in temp:
            if temp[item].lower() == "true":
                temp[item] = True
            elif temp[item].lower() == "false":
                temp[item] = False
            elif temp[item].lower() == "none":
                temp[item] = None
            elif re.search("^\d+\.\d+$",temp[item].lower()):
                temp[item] = float(temp[item])
            elif re.search("^[\d]+$",temp[item].lower()):
                temp[item] = int(temp[item])
        config[sec] = temp
    print(config["main"])
    pocr = PaddleOCR(**config["main"])

# 上传文件
@app.route('/ocr', methods=['POST'])
def upload_file():
    global pocr
    global config
    f = request.files.get('img')
    if f is None:
        # 表示没有发送文件
        return "未上传文件"
    # 设置保存路径
    save_father_path = 'images'
    img_path = os.path.join(save_father_path, str(
        uuid.uuid1()) + splitext(f.filename)[-1])
    if not os.path.exists(save_father_path):
        os.makedirs(save_father_path)
    f.save(img_path)
    print(img_path)
    res = pocr.ocr(img_path, **config["ocr"])
    os.remove(img_path)
    return str(res)


if __name__ == '__main__':
    init()
    # 启动服务，并指定端口号
    app.run(**config["web"])

配置文件config.ini，对应的方法参数体。

[main]
det_model_dir = model/det
rec_model_dir = model/rec/ch
cls_model_dir = model/cls
rec_char_dict_path = model/ppocr_keys_v1.txt
use_gpu = False
[ocr]
det = True
rec = True
cls = False
[web]
port = 8080
host = 127.0.0.1
debug = None
load_dotenv = True

模型放置在model下（必须：ppocr_keys_v1.txt是从paddleocr中提取出来的，其他模型缺失可以自动下载）。结构如下：

image.png
PyInstaller Hook文件hook-ctypes.macholib.py

from PyInstaller.utils.hooks import copy_metadata
datas = copy_metadata('prettytable')

打包脚本,这里的G:\Miniconda3\envs\pppocr替换为你实际pppocr环境地址。打包完成放置在dist。

conda activate pppocr
pyinstaller -D -y --clean --exclude matplotlib -p G:\Miniconda3\envs\pppocr\Lib\site-packages\paddleocr;G:\Miniconda3\envs\pppocr\Lib\site-packages\paddle\libs ocr.py -i scr2txt.ico --add-binary G:\Miniconda3\envs\pppocr\Lib\site-packages\paddle\libs;. --add-data .\model;.\model --add-data .\config.ini;.\ --additional-hooks-dir=.