# fatemezamanian/yolov5-fruit-detector architecture

> Architecture diagram of the GitHub repository fatemezamanian/yolov5-fruit-detector, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-09-21). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/fatemezamanian/yolov5-fruit-detector
- Repository: https://github.com/fatemezamanian/yolov5-fruit-detector

## Overview

##### Main Components
- Data Layer
– Raw datasets (coco, VOC, Argoverse, etc.) under data/
– Data-preprocessing & augmentation (utils/datasets.py, utils/autoanchor.py)
- Model Layer
– Core model definitions (models/yolo.py, models/common.py, models/experimental.py)
– Predefined configs (models/hub/*.yaml)
– Weight files (weights/*.pt)
- Training Pipeline
– train.py (trains YOLO models with hyperparameters in data/hyp*.yaml)
– Logging & metrics (utils/loss.py, utils/metrics.py, utils/plots.py, utils/wandb_logging/)
- Inference & Export
– detect.py (image/video inference)
– export.py (ONNX, Torchscript via models/export.py)
– YoloToONNX.ipynb notebook
- Frontend UI
– Qt form (ui/form.ui) launched by main.py
– main.py handles user input (image/video), calls detect.py/detector.py
- REST API Server
– utils/flask_rest_api/restapi.py with example_request.py
- Deployment & Ops
– AWS helpers (utils/aws/) for S3, EC2 userdata, resume hooks
– Google App Engine config (utils/google_app_engine/)
– hubconf.py (exposes PyTorch Hub interface)

##### Relationships & Data Flows
Raw data → preprocessing → training → model weights → inference
Weights → export → ONNX/TorchScript
- Control Flow
UI (main.py) → detector.py → model (loaded via hubconf.py) → display results
REST API → detect function → returns JSON/HTTP response
- Deployment Flow
git push → cloud build (GAE Dockerfile) → running REST API service
AWS scripts → provision/auto-scale training or inference endpoints

##### Architectural Patterns
- Modular ML Pipeline: clear separation of data, training, inference, and export modules
- MVC-style UI: form.ui (view) ↔ main.py/controller ↔ detector/model
- Adapter Pattern: hubconf.py adapts local models to PyTorch Hub API
- Micro-services style: optional REST API layer decoupled from UI

##### Key Technologies & Frameworks
- Python 3.6+, PyTorch 1.7+
- YAML for configs (data/, models/hub/)
- Flask for REST API
- Qt (PyQt) for desktop UI
- AWS shell scripts, GAE Dockerfiles for deployment
- Weights management via shell scripts in weights/

## Diagram (Mermaid)

```mermaid
flowchart TD
    subgraph "Data & Preprocessing"
        DataStore["Datasets (coco, VOC, Argoverse)"]:::data
        Preprocess["Preprocessing & Augmentation"]:::data
    end

    subgraph "Model & Training"
        CoreModel["Core Model Definitions"]:::model
        HubConfigs["Predefined Configs (YAML)"]:::model
        WeightsStore["Weights Store"]:::model
        TrainScript["Training Script (train.py)"]:::model
        HypConfigs["Hyperparameter Configs (YAML)"]:::model
        Logging["Logging & Metrics"]:::model
    end

    subgraph "Inference & Export"
        Detect["detect.py / detector.py"]:::infra
        ExportModule["Export Module"]:::infra
        Notebook["YoloToONNX.ipynb"]:::infra
    end

    subgraph "UI & API"
        UIForm["Qt Form (ui/form.ui)"]:::ui
        MainApp["main.py"]:::ui
        HubAdapter["hubconf.py"]:::ui
        RESTAPI["Flask REST API"]:::ui
        ExampleReq["example_request.py"]:::ui
    end

    subgraph "Deployment & Ops"
        AWS["AWS Helpers"]:::ops
        GAE["Google App Engine Config"]:::ops
    end

    DataStore -->|prepares| Preprocess
    Preprocess -->|feeds| TrainScript
    HubConfigs -->|configures| CoreModel
    CoreModel -->|used by| TrainScript
    HypConfigs -->|hyperparams| TrainScript
    TrainScript -->|produces| WeightsStore
    TrainScript -->|logs to| Logging
    WeightsStore -->|loaded by| Detect
    Detect -->|exports| ExportModule
    ExportModule -->|notebook uses| Notebook
    UIForm -->|input to| MainApp
    MainApp -->|calls| Detect
    MainApp -->|loads| HubAdapter
    RESTAPI -->|invokes| Detect
    MainApp -->|serves| RESTAPI
    AWS -.->|provisions| TrainScript
    AWS -.->|scales| Detect
    GAE -.->|deploys| RESTAPI

    classDef data fill:#D0E6FA,stroke:#0B5394,color:#0B5394;
    classDef model fill:#D8EAD9,stroke:#38761D,color:#38761D;
    classDef infra fill:#FDE9D9,stroke:#E69138,color:#E69138;
    classDef ui fill:#EAD1DC,stroke:#741B47,color:#741B47;
    classDef ops fill:#EDEDED,stroke:#7F7F7F,color:#7F7F7F;

    class DataStore,Preprocess data;
    class CoreModel,HubConfigs,WeightsStore,TrainScript,HypConfigs,Logging model;
    class Detect,ExportModule,Notebook infra;
    class UIForm,MainApp,HubAdapter,RESTAPI,ExampleReq ui;
    class AWS,GAE ops;

    click DataStore "https://github.com/fatemezamanian/yolov5-fruit-detector/tree/master/data/"
    click Preprocess "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/datasets.py"
    click Preprocess "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/autoanchor.py"
    click CoreModel "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/models/yolo.py"
    click CoreModel "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/models/common.py"
    click CoreModel "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/models/experimental.py"
    click HubConfigs "https://github.com/fatemezamanian/yolov5-fruit-detector/tree/master/models/hub/"
    click WeightsStore "https://github.com/fatemezamanian/yolov5-fruit-detector/tree/master/weights/"
    click WeightsStore "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/weights/download_weights.sh"
    click TrainScript "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/train.py"
    click HypConfigs "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/data/hyp.finetune.yaml"
    click HypConfigs "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/data/hyp.finetune_objects365.yaml"
    click HypConfigs "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/data/hyp.scratch.yaml"
    click Logging "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/loss.py"
    click Logging "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/metrics.py"
    click Logging "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/plots.py"
    click Logging "https://github.com/fatemezamanian/yolov5-fruit-detector/tree/master/utils/wandb_logging/"
    click Detect "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/detect.py"
    click Detect "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/detector.py"
    click ExportModule "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/models/export.py"
    click Notebook "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/YoloToONNX.ipynb"
    click UIForm "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/ui/form.ui"
    click MainApp "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/main.py"
    click HubAdapter "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/hubconf.py"
    click RESTAPI "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/flask_rest_api/restapi.py"
    click ExampleReq "https://github.com/fatemezamanian/yolov5-fruit-detector/blob/master/utils/flask_rest_api/example_request.py"
    click AWS "https://github.com/fatemezamanian/yolov5-fruit-detector/tree/master/utils/aws/"
    click GAE "https://github.com/fatemezamanian/yolov5-fruit-detector/tree/master/utils/google_app_engine/"
```
