📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
Add tips when successfully launched.
SWHLd41572a85251
diff --git a/ocrweb/README.md b/ocrweb/README.mdindex 0fd6806..e810662 100755--- a/ocrweb/README.md+++ b/ocrweb/README.md@@ -12,7 +12,6 @@- [简要说明](#简要说明)- [桌面版使用教程](#桌面版使用教程)- [界面版使用步骤](#界面版使用步骤)- - [API版使用步骤](#api版使用步骤)### 简要说明@@ -53,143 +52,3 @@```3. 使用- 浏览器打开`http://localhost:9003/`,enjoy it.--### API版使用步骤-1. 安装`rapidocr_web[api]`- ```bash- $ pip install rapidocr_web[api]- ```-2. 运行- - 用法:- ```bash- $ rapidocr_api -h- usage: rapidocr_api [-h] [-ip IP] [-p PORT]-- optional arguments:- -h, --help show this help message and exit- -ip IP, --ip IP IP Address- -p PORT, --port PORT IP port- ```- - 示例:- ```bash- $ rapidocr_api -ip 0.0.0.0 -p 9003- ```-3. 使用(本质就是发送一个POST请求,其他语言同理)- - 以文件的方式发送请求- ```python- import requests-- url = 'http://localhost:9003/ocr'- img_path = '../python/tests/test_files/ch_en_num.jpg'-- with open(img_path, 'rb') as f:- file_dict = {'image_file': (img_path, f, 'image/png')}- response = requests.post(url, files=file_dict, timeout=60)-- print(response.json())- ```- - 以`base64`方式发送post请求- ```python- import base64- import requests-- url = 'http://localhost:9003/ocr'- img_path = '../python/tests/test_files/ch_en_num.jpg'-- with open(img_path, 'rb') as fa:- img_str = base64.b64encode(fa.read())-- payload = {'image_data': img_str}- resp = requests.post(url, data=payload)-- print(resp.json())- ```-4. API输出- - 示例结果:- <details>- <summary>详情</summary>-- ```json- {- "0": {- "rec_txt": "香港深圳抽血,",- "dt_boxes": [- [265, 18],- [472, 231],- [431, 271],- [223, 59]- ],- "score": "0.8175641223788261"- },- "1": {- "rec_txt": "专业查性别",- "dt_boxes": [- [388, 15],- [636, 257],- [587, 307],- [339, 65]- ],- "score": "0.8293875356515249"- },- "2": {- "rec_txt": "专业鉴定B超单",- "dt_boxes": [- [215, 84],- [509, 413],- [453, 463],- [159, 134]- ],- "score": "0.8626169338822365"- },- "3": {- "rec_txt": "b超仪器查性别",- "dt_boxes": [- [128, 135],- [430, 478],- [366, 534],- [64, 192]- ],- "score": "0.8449362441897392"- },- "4": {- "rec_txt": "加微信eee",- "dt_boxes": [- [58, 189],- [268, 450],- [209, 498],- [0, 236]- ],- "score": "0.8176911813872201"- },- "5": {- "rec_txt": "可邮寄",- "dt_boxes": [- [493, 261],- [617, 384],- [577, 423],- [454, 300]- ],- "score": "0.7494261413812637"- }- }- ```- </details>-- - 输出结果说明:- - 如果图像中存在文字,则会输出json格式,具体格式介绍如下:- ```python- {- "0": {- "rec_txt": "香港深圳抽血,", # 识别的文本- "dt_boxes": [ # 依次为左上角 → 右上角 → 右下角 → 左下角- [265, 18],- [472, 231],- [431, 271],- [223, 59]- ],- "score": "0.8175641223788261" # 置信度- }- }- ```- - 如果没有检测到文字,则会输出空json(`{}`)。-5. **!!说明:OCR的输出结果为最原始结果,大家可按需进一步扩展。**diff --git a/ocrweb/rapidocr_web/api.py b/ocrweb/rapidocr_web/api.pydeleted file mode 100644index 01f0052..0000000--- a/ocrweb/rapidocr_web/api.py+++ /dev/null@@ -1,76 +0,0 @@-# -*- encoding: utf-8 -*--# @Author: SWHL-# @Contact: [email protected]-import argparse-import base64-import io-import json-from pathlib import Path--import cv2-import numpy as np-import uvicorn-from fastapi import FastAPI, Form, UploadFile-from PIL import Image-from rapidocr_onnxruntime import RapidOCR---class OCRAPIUtils():- def __init__(self) -> None:- self.ocr = RapidOCR()-- def __call__(self, img):- img = np.array(img)- img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)-- ocr_res, _ = self.ocr(img)- if not ocr_res:- return json.dumps({})-- out_dict = {str(i): {'rec_txt': rec,- 'dt_boxes': dt_box,- 'score': score}- for i, (dt_box, rec, score) in enumerate(ocr_res)}- return json.dumps(out_dict, indent=2, ensure_ascii=False)---app = FastAPI()-processor = OCRAPIUtils()--[email protected]("/")-async def root():- return {'message': 'Welcome to RapidOCR Server!'}--[email protected]('/ocr')-async def ocr(image_file: UploadFile = None, image_data: str = Form(None)):- if image_file:- img = Image.open(image_file.file)- elif image_data:- img_bytes = str.encode(image_data)- img_b64decode = base64.b64decode(img_bytes)- img = Image.open(io.BytesIO(img_b64decode))- else:- raise ValueError(- 'When sending a post request, data or files must have a value.')-- ocr_res = processor(img)- return ocr_res---def main():- parser = argparse.ArgumentParser('rapidocr_api')- parser.add_argument('-ip', '--ip', type=str, default='0.0.0.0',- help='IP Address')- parser.add_argument('-p', '--port', type=int, default=9003,- help='IP port')- args = parser.parse_args()-- cur_file_path = Path(__file__).resolve()- app_path = f'{cur_file_path.parent.name}.{cur_file_path.stem}:app'- uvicorn.run(app_path, host=args.ip, port=args.port, reload=True)---if __name__ == '__main__':- main()diff --git a/ocrweb/rapidocr_web/api.spec b/ocrweb/rapidocr_web/api.specdeleted file mode 100644index a61a5f2..0000000--- a/ocrweb/rapidocr_web/api.spec+++ /dev/null@@ -1,71 +0,0 @@-# -*- mode: python ; coding: utf-8 -*--from pathlib import Path--import rapidocr_onnxruntime--block_cipher = None--package_name = 'rapidocr_onnxruntime'-install_dir = Path(rapidocr_onnxruntime.__file__).resolve().parent--onnx_paths = list(install_dir.rglob('*.onnx'))-yaml_paths = list(install_dir.rglob('*.yaml'))--onnx_add_data = [(str(v.parent), f'{package_name}/{v.parent.name}')- for v in onnx_paths]--yaml_add_data = []-for v in yaml_paths:- if package_name == v.parent.name:- yaml_add_data.append((str(v.parent / '*.yaml'), package_name))- else:- yaml_add_data.append(- (str(v.parent / '*.yaml'), f'{package_name}/{v.parent.name}'))--add_data = list(set(yaml_add_data + onnx_add_data))--a = Analysis(- ['api.py'],- pathex=[],- binaries=[],- datas=[],- hiddenimports=[],- hookspath=[],- hooksconfig={},- runtime_hooks=[],- excludes=[],- win_no_prefer_redirects=False,- win_private_assemblies=False,- cipher=block_cipher,- noarchive=False,-)-pyz = PYZ(a.pure, a.zipped_data, cipher=block_cipher)--exe = EXE(- pyz,- a.scripts,- [],- exclude_binaries=True,- name='api',- debug=False,- bootloader_ignore_signals=False,- strip=False,- upx=True,- console=True,- disable_windowed_traceback=False,- argv_emulation=False,- target_arch=None,- codesign_identity=None,- entitlements_file=None,- icon=['./static/css/favicon.ico'],-)-coll = COLLECT(- exe,- a.binaries,- a.zipfiles,- a.datas,- strip=False,- upx=True,- upx_exclude=[],- name='api',-)diff --git a/ocrweb/rapidocr_web/ocrweb.py b/ocrweb/rapidocr_web/ocrweb.pyindex 86de9dd..c3fc1b3 100644--- a/ocrweb/rapidocr_web/ocrweb.py+++ b/ocrweb/rapidocr_web/ocrweb.py@@ -40,6 +40,7 @@ def main():help='IP port')args = parser.parse_args()+ print('Successfully launched and visit https://localhost:9003 to view.')server = make_server(args.ip, args.port, app)server.serve_forever()diff --git a/ocrweb/requirements.txt b/ocrweb/requirements.txtindex 113a704..7b13fb3 100644--- a/ocrweb/requirements.txt+++ b/ocrweb/requirements.txt@@ -4,5 +4,3 @@ Flask>=2.1.0rapidocr_onnxruntimeget_pypi_latest_versionwheel-fastapi-uvicorn[standard]diff --git a/ocrweb/setup.py b/ocrweb/setup.pyindex bab3f16..c414ff0 100644--- a/ocrweb/setup.py+++ b/ocrweb/setup.py@@ -53,20 +53,15 @@ setuptools.setup('ocr,text_detection,text_recognition,db,onnxruntime,paddleocr,openvino,rapidocr'],classifiers=[- 'Programming Language :: Python :: 3.6','Programming Language :: Python :: 3.7','Programming Language :: Python :: 3.8','Programming Language :: Python :: 3.9','Programming Language :: Python :: 3.10',],- python_requires='>=3.6,<=3.10',+ python_requires='>=3.7,<=3.10',entry_points={'console_scripts': [f'{MODULE_NAME}={MODULE_NAME}.ocrweb:main',- f'rapidocr_api={MODULE_NAME}.api:main'],},- extras_require={- 'api': ['fastapi', 'uvicorn[standard]']- })