AgentCLPR
简介
- 一个基于 ONNXRuntime、AgentOCR 和 License-Plate-Detector 项目开发的中国车牌检测识别系统。
车牌识别效果
-
支持多种车牌的检测和识别(其中单层车牌识别效果较好):
-
单层车牌:
[[[[373, 282], [69, 284], [73, 188], [377, 185]], ['苏E05EV8', 0.9923506379127502]]] [[[[393, 278], [318, 279], [318, 257], [393, 255]], ['VA30093', 0.7386096119880676]]] [[[[[487, 366], [359, 372], [361, 331], [488, 324]], ['皖K66666', 0.9409016370773315]]]] [[[[304, 500], [198, 498], [199, 467], [305, 468]], ['鲁QF02599', 0.995299220085144]]] [[[[309, 219], [162, 223], [160, 181], [306, 177]], ['使198476', 0.9938704371452332]]] [[[[957, 918], [772, 920], [771, 862], [956, 860]], ['陕A06725D', 0.9791222810745239]]] -
双层车牌:
[[[[399, 298], [256, 301], [256, 232], [400, 230]], ['浙G66666', 0.8870148431461757]]] [[[[398, 308], [228, 305], [227, 227], [398, 230]], ['陕A00087', 0.9578166644088313]]] [[[[352, 234], [190, 244], [190, 171], [352, 161]], ['宁A66666', 0.9958433652812175]]]
-
快速使用
-
快速安装
# 安装 AgentCLPR $ pip install agentclpr # 根据设备平台安装合适版本的 ONNXRuntime # CPU 版本(推荐非 win10 系统,无 CUDA 支持的设备安装) $ pip install onnxruntime # GPU 版本(推荐有 CUDA 支持的设备安装) $ pip install onnxruntime-gpu # DirectML 版本(推荐 win10 系统的设备安装,可实现通用的显卡加速) $ pip install onnxruntime-directml # 更多版本的安装详情请参考 ONNXRuntime 官网
-
简单调用:
# 导入 CLPSystem 模块 from agentclpr import CLPSystem # 初始化车牌识别模型 clp = CLPSystem() # 使用模型对图像进行车牌识别 results = clp('test.jpg')
-
服务器部署:
-
启动 AgentCLPR Server 服务
$ agentclpr server
-
Python 调用
import cv2 import json import base64 import requests # 图片 Base64 编码 def cv2_to_base64(image): data = cv2.imencode('.jpg', image)[1] image_base64 = base64.b64encode(data.tobytes()).decode('UTF-8') return image_base64 # 读取图片 image = cv2.imread('test.jpg') image_base64 = cv2_to_base64(image) # 构建请求数据 data = { 'image': image_base64 } # 发送请求 url = "http://127.0.0.1:5000/ocr" r = requests.post(url=url, data=json.dumps(data)) # 打印预测结果 print(r.json())
-
Metadata
Release files for agentclpr 1.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentclpr-1.1.0.tar.gz | 9.6 MB | Without provenance | Details for agentclpr-1.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentclpr-1.1.0-py3-none-any.whl | Python 3 | none | any | Details for agentclpr-1.1.0-py3-none-any.whl |
Total release size: 19.3 MB
Release files / agentclpr-1.1.0.tar.gz
| Download URL | agentclpr-1.1.0.tar.gz |
|---|---|
| Size | 9.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a7cf329c3f4f13ff8bb96775206fe32cb69c6aa17c3ee4c7c7aea00e4cf4878c
|
|
BLAKE2b-256 checksum How to use checksums |
9695de0856c39a77e13871ae94c55fe2777e8eb9f2ede86509361e3e5f8994ea
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.2 importlib_metadata/4.6.4 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.1
|
Release files / agentclpr-1.1.0-py3-none-any.whl
| Download URL | agentclpr-1.1.0-py3-none-any.whl |
|---|---|
| Size | 9.6 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0b5f86d9599692156a997a17be3a6536a8ba07c285f634cc9af7c982c8cee4d3
|
|
BLAKE2b-256 checksum How to use checksums |
51116cbc13b449f29b4f008bb7427cfd2f5e60959cd722aec31d5b184e5bedf7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.2 importlib_metadata/4.6.4 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.1
|
Security for agentclpr 1.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.