# xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue architecture

> Architecture diagram of the GitHub repository xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-14). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue
- Repository: https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue

## Overview

##### Project type and purpose
- This is a full-stack AI algorithm “middle platform” (中台) system combining:
- A Java Spring Boot backend exposing REST APIs
- A Vue.js frontend single-page app
- Python (and optional C++) inference modules for YOLOv8 on GPU/CPU
- Shell scripts to glue platform components
- Docker for containerized deployment
- Purpose: let Java developers upload/manage deep-learning models, schedule video inference tasks, perform real-time inference (via ONNX or TensorRT), push inference frames/results to a media server and notify downstream systems.

##### File structure
- Top-level:
- data/… – AI model files, platform docs, front-end code, OS-specific inference scripts, SQL schema, Dockerfile
- src/ – Java Spring Boot monolith organized by layers (controller, service, dao, mapper, etc.), AOP, annotation, code-generation templates
- img/ – architecture and UI screenshots
- pom.xml, mvnw – Maven build
- Front-end under data/front_code (Vue)
- Linux and Windows folders under data/linux and data/windows host separate script sets and Python/C++ inference code
- Resources: application.properties, FreeMarker templates (codeGen), MyBatis configs
- Deployment: Dockerfile under data/docker, shell run scripts under data/linux/... and data/windows/…

##### README for additional insights
- Lists external dependencies: MySQL, Redis, MongoDB, RocketMQ, Minio, ZLM media server, FFmpeg, Nginx.

##### Main components
a. Frontend
- Vue.js app (npm)
- Served by Nginx (or local dev server)
- Connects to backend via REST (HTTP/JSON), RTMP/FLV/HLS for video streams
b. Backend (Java Spring Boot)
- Controllers → Services → DAOs (MyBatis + Mongo + Redis)
- AOP/annotations for logging, encryption, validation
- Code-Gen module (FreeMarker)
- Message producers/consumers to RocketMQ
- File storage client to Minio
- ShellInvoker: triggers inference .sh/.bat scripts
c. Inference Workers
- Python modules: ONNXRuntime, PyTorch, Ultralytics Yolov8, OpenCV, FFmpeg
- Optional C++ code (TensorRT, DeepStream)
- Shell scripts launch inference; workers read video (local path or stream), run inference, generate frames + metadata
- Push inference images/results to Minio + RocketMQ
d. Media Server & Streaming
- FFmpeg (inside Python worker) pushes to ZLMediaKit over RTMP/FLV
- ZLMediaKit streams to web front-end
e. Data Stores & Middleware
- MySQL – system metadata, user, task, model tables
- MongoDB – optional document storage
- Redis – cache, locks
- RocketMQ – event bus for task start, inference results, failure retries
- Minio – object store for model binaries, inference snapshots
f. Deployment Infrastructure
- Docker container (Ubuntu20.04 + Java, Python, CUDA, cuDNN, TensorRT)
- GPU node (e.g. Nvidia T4)
- Kubernetes or plain Docker run commands (with --gpus)
- Nginx container serves frontend

##### Relationships and interactions
1. User → Vue.js UI
2. UI → HTTP → Spring Boot REST controllers
3. Controllers delegate to services → persist to MySQL/Mongo; produce task messages to RocketMQ
4. Service triggers inference shell script (with modelKey, shellKey)
5. Shell launches Python worker (or C++ executable)
6. Worker reads video stream/file, runs inference →
- FFmpeg pushes processed frames to ZLMediaKit
- Worker uploads snapshot images + metadata to Minio
- Worker publishes inference result to RocketMQ
7. Spring Boot consumers (RocketMQ listeners) consume inference results → store alarm records, logs, push HTTP notifications to customers
8. UI requests video streams from ZLMediaKit and reads alarm/task data from backend

##### Architectural patterns and design principles
- Layered architecture (Presentation → API → Business → Persistence)
- Aspect-Oriented Programming for cross-cutting concerns (logging, encryption)
- Template-based code generation (FreeMarker)
- Event-driven integration via RocketMQ
- Polyglot runtimes: Java, Python, Shell, optional C++
- OS abstraction: folder structure under data/linux vs data/windows
- Containerization and immutable infrastructure

##### Detailed elements
- Frontend: Vue.js → Nginx
- API Gateway: SpringBoot REST
- Business logic: Service layer, AOP modules
- Persistence: MySQL, MongoDB, Redis
- Event Bus: RocketMQ producers & consumers
- Object Store: Minio
- Inference: Shell scripts invoking Python ONNXRuntime & TensorRT modules
- Streaming: FFmpeg → ZLMediaKit → browser
- Deployment: Docker host with GPU, volumes, GPU flags

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Frontend Layer
    subgraph "Frontend Layer"
        direction TB
        Frontend["Vue.js SPA"]:::frontend
        Nginx["Nginx (Static Server)"]:::frontend
    end

    %% Backend Layer
    subgraph "Backend Layer"
        direction TB
        SpringBootAPI["SpringBoot REST API"]:::backend
        Controller["Controllers"]:::backend
        ServiceLayer["Service Layer"]:::backend
        DAO["DAOs"]:::backend
        Mapper["MyBatis Mappers"]:::backend
        AOPAnno["Annotations"]:::backend
        Aspects["AOP Aspects"]:::backend
        CodeGen["CodeGen Module"]:::backend
        Templates["FreeMarker Templates"]:::backend
        MQProducers["RocketMQ Producers"]:::backend
        MQConsumers["RocketMQ Consumers"]:::backend
        MinioUtil["Minio Client Utility"]:::backend
        ShellExecutor["ShellInvoker Utility"]:::backend
        AppConfig["Spring Boot Config"]:::backend
    end

    %% Inference Workers
    subgraph "Inference Workers (Linux)"
        direction TB
        ONNXShell["ONNX Shell Script"]:::inference
        ONNXWorker["ONNX Python Worker"]:::inference
        TRTShell["TensorRT Shell Script"]:::inference
        TRTWorker["TensorRT Python Worker"]:::inference
    end

    %% Deployment Container
    subgraph "Docker Container w/ GPU" 
        direction TB
        Dockerfile["Dockerfile"]:::infra
        RunScript["Run Script (Linux)"]:::infra
    end

    %% External Services
    subgraph "External Services"
        direction TB
        MySQL["MySQL"]:::datastore
        MongoDB["MongoDB"]:::datastore
        Redis["Redis"]:::datastore
        RocketMQ["RocketMQ"]:::datastore
        Minio["Minio Object Store"]:::datastore
        ZLM["ZLMediaKit"]:::datastore
    end

    %% UI Streaming
    Browser["User Browser"]:::frontend

    %% Connections
    Browser -->|HTTP/REST| Frontend
    Frontend -->|serves SPA| Nginx
    Frontend -->|HTTP/REST| SpringBootAPI
    SpringBootAPI -->|calls| Controller
    Controller -->|calls| ServiceLayer
    ServiceLayer -->|JDBC/ORM| DAO
    DAO -->|SQL| MySQL
    ServiceLayer -->|calls| Mapper
    Mapper -->|SQL| MySQL
    ServiceLayer -->|uses| AOPAnno
    ServiceLayer -->|uses| Aspects
    ServiceLayer -->|executes| CodeGen
    CodeGen -->|reads| Templates
    ServiceLayer -->|send| MQProducers
    ServiceLayer -->|invoke| ShellExecutor
    ShellExecutor -->|runs| ONNXShell
    ShellExecutor -->|runs| TRTShell
    ONNXShell -->|launch| ONNXWorker
    TRTShell -->|launch| TRTWorker
    ONNXWorker -->|upload| Minio
    TRTWorker -->|upload| Minio
    ONNXWorker -->|publish| RocketMQ
    TRTWorker -->|publish| RocketMQ
    ONNXWorker -->|stream RTMP| ZLM
    TRTWorker -->|stream RTMP| ZLM
    MQConsumers -->|consume| RocketMQ
    MQConsumers -->|write| MySQL
    MQConsumers -->|write| MongoDB
    MQConsumers -->|cache| Redis
    MQConsumers -->|notify| Browser
    Browser -->|HLS/FLV| ZLM

    %% Deployment links
    SpringBootAPI --- Dockerfile
    ONNXWorker --- Dockerfile
    TRTWorker --- Dockerfile
    Dockerfile --> RunScript

    %% Click Events
    click Frontend "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/front_code/alg_vue.zip"
    click Controller "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/controller"
    click ServiceLayer "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/service"
    click DAO "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/dao"
    click Mapper "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/mapper"
    click AOPAnno "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/annotation"
    click Aspects "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/aop"
    click CodeGen "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/codeGen"
    click Templates "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/resources/templates/genCodeMysql"
    click MQProducers "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/messagePush"
    click MQConsumers "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/src/main/java/cn/kafuka/rocketMq"
    click MinioUtil "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/src/main/java/cn/kafuka/util/MinioUtil.java"
    click ShellExecutor "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/src/main/java/cn/kafuka/util/ShellCommandExecutorUtil.java"
    click ONNXWorker "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/linux/algcenter/yolo/onnx_infer/yolov8_detect_onnx.py"
    click ONNXShell "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/linux/algcenter/yolo/onnx_infer/run_yolov8_detect_onnx.sh"
    click TRTWorker "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/linux/algcenter/yolo/tensorrt_infer/yolov8_detect_tensorrt.py"
    click TRTShell "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/linux/algcenter/yolo/tensorrt_infer/run_yolov8_detect_tensorrt.sh"
    click Dockerfile "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/data/linux/docker/Dockerfile"
    click RunScript "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/linux/algcenter/run.sh"
    click SQLSchema "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/data/sql/algrithm_center.sql"
    click Diagrams "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/tree/master/img/"
    click AppConfig "https://github.com/xiaoyeshenger/java_pytorch_onnx_tensorrt_yolov8_vue/blob/master/src/main/resources/application.properties"

    %% Styles
    classDef frontend fill:#D4BFFF,stroke:#888
    classDef backend fill:#A9D0F5,stroke:#333
    classDef inference fill:#C1E1C1,stroke:#2E8B57
    classDef datastore fill:#F7D358,stroke:#B8860B
    classDef infra fill:#D3D3D3,stroke:#666
```
