conda paddleHub 一键安装

步骤
1、window环境下先安装miniconda x64
2、运行下面脚本安装，启动服务
3、python测试验证

install.bat脚本

@echo off
:M
cls
echo ┌─────────────────────────────────────────────────────────────────────┐
echo │                                                                     │
echo │  操作选项：                                                         │
echo │      1.安装环境                                                     │
echo │      2.启动服务                                                     │
echo │                                                                     │
echo └─────────────────────────────────────────────────────────────────────┘

cd %~dp0
%~d0

set env=pphub

set /p main=输入命令选项：
if %main% EQU 1 goto install
if %main% EQU 2 goto server
goto M

:install
conda create -n %env% python=3.7 && conda activate %env% && pip install --upgrade paddlepaddle -i https://mirror.baidu.com/pypi/simple && pip install --upgrade paddlehub -i https://mirror.baidu.com/pypi/simple
goto M

:server
conda activate %env% && hub serving start -m chinese_ocr_db_crnn_mobile
goto M

python测试图片ocr识别

import requests
import json
import base64

file_path = r"C:\Users\Administrator\Desktop\微信截图_20220209192322.png"

with open(file_path,"rb") as f:
    data = f.read()
    data = base64.b64encode(data).decode('utf8')
    data = {'images':[data]}    
    headers = {"Content-type": "application/json"}
    url = "http://127.0.0.1:8866/predict/chinese_ocr_db_crnn_mobile"
    r = requests.post(url=url, headers=headers, data=json.dumps(data))
    # 打印预测结果
    print(r.json())

附：
paddleHub 模型库：https://www.paddlepaddle.org.cn/hubsearch?filter=en_category