# arpit-kumar05/major_project architecture

> Architecture diagram of the GitHub repository arpit-kumar05/major_project, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/arpit-kumar05/major_project
- Repository: https://github.com/arpit-kumar05/major_project

## Overview

This is a potato-leaf disease classifier with both a Streamlit interface and a separate upload-prediction script. The main workflow accepts an image or webcam frame, preprocesses it, runs CNN inference, and displays a class and confidence. A separate training workflow loads PlantVillage images, trains and validates a CNN, and saves weights. The UI also documents dataset statistics and live webcam support. The graph reflects shown code and README capabilities; training and inference define separate model classes, and no shared preprocessing or class-metadata wiring is shown.

Main entry points: [`app.py`](https://github.com/arpit-kumar05/major_project/blob/main/app.py) (Detection dashboard), [`predict.py`](https://github.com/arpit-kumar05/major_project/blob/main/predict.py) (Upload predictor), [`train.py`](https://github.com/arpit-kumar05/major_project/blob/main/train.py) (Train and validate), [`models/plant_disease_model.pth`](https://github.com/arpit-kumar05/major_project/blob/main/models/plant_disease_model.pth) (Saved model weights)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_training["Model training"]
  node_train_process["Train and validate<br/>[train.py]"]
  node_trained_cnn["Training CNN<br/>[train.py]"]
end

subgraph group_inference["Prediction"]
  node_app_preprocess["Image preprocessing<br/>[app.py]"]
  node_app_cnn["Inference CNN<br/>[app.py]"]
  node_app_results["Class and confidence<br/>[app.py]"]
  node_predict_preprocess["Image preprocessing<br/>[predict.py]"]
  node_predict_cnn["Prediction CNN<br/>[predict.py]"]
end

subgraph group_experience["User interfaces"]
  node_streamlit_app["Detection dashboard<br/>[app.py]"]
  node_webcam["Live webcam processor<br/>[app.py]"]
  node_dataset_stats["Dataset statistics view<br/>[app.py]"]
  node_upload_app["Upload predictor<br/>[predict.py]"]
  node_predict_results["Prediction display<br/>[predict.py]"]
end

subgraph group_support["Dataset and state"]
  node_train_data[("PlantVillage images")]
  node_weights[("Saved model weights")]
  node_class_metadata["Class metadata helpers<br/>[utils.py]"]
end

node_user(("User"))
node_camera(("Camera"))

node_train_process -->|"loads and splits"| node_train_data
node_train_process -->|"trains and validates"| node_trained_cnn
node_train_process -->|"saves weights"| node_weights
node_user -->|"submits image"| node_streamlit_app
node_streamlit_app -->|"loads weights"| node_weights
node_streamlit_app -->|"prepares image"| node_app_preprocess
node_app_preprocess -->|"provides tensor"| node_app_cnn
node_streamlit_app -->|"runs prediction"| node_app_cnn
node_app_cnn -->|"returns probabilities"| node_app_results
node_app_results -->|"displays result"| node_streamlit_app
node_camera -->|"sends frames"| node_webcam
node_webcam -->|"predicts each frame"| node_app_results
node_streamlit_app -->|"shows class counts"| node_dataset_stats
node_user -->|"uploads image"| node_upload_app
node_upload_app -->|"loads weights"| node_weights
node_upload_app -->|"prepares image"| node_predict_preprocess
node_upload_app -->|"runs prediction"| node_predict_cnn
node_predict_cnn -->|"returns probabilities"| node_predict_results
node_predict_results -->|"displays result"| node_upload_app

click node_train_data "https://github.com/arpit-kumar05/major_project/tree/main/dataset/PlantVillage"
click node_train_process "https://github.com/arpit-kumar05/major_project/blob/main/train.py"
click node_trained_cnn "https://github.com/arpit-kumar05/major_project/blob/main/train.py"
click node_weights "https://github.com/arpit-kumar05/major_project/blob/main/models/plant_disease_model.pth"
click node_streamlit_app "https://github.com/arpit-kumar05/major_project/blob/main/app.py"
click node_app_preprocess "https://github.com/arpit-kumar05/major_project/blob/main/app.py"
click node_app_cnn "https://github.com/arpit-kumar05/major_project/blob/main/app.py"
click node_app_results "https://github.com/arpit-kumar05/major_project/blob/main/app.py"
click node_webcam "https://github.com/arpit-kumar05/major_project/blob/main/app.py"
click node_dataset_stats "https://github.com/arpit-kumar05/major_project/blob/main/app.py"
click node_upload_app "https://github.com/arpit-kumar05/major_project/blob/main/predict.py"
click node_predict_preprocess "https://github.com/arpit-kumar05/major_project/blob/main/predict.py"
click node_predict_cnn "https://github.com/arpit-kumar05/major_project/blob/main/predict.py"
click node_predict_results "https://github.com/arpit-kumar05/major_project/blob/main/predict.py"
click node_class_metadata "https://github.com/arpit-kumar05/major_project/blob/main/utils.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_train_process,node_trained_cnn,node_user toneBlue
class node_app_preprocess,node_app_cnn,node_app_results,node_predict_preprocess,node_predict_cnn toneAmber
class node_streamlit_app,node_webcam,node_dataset_stats,node_upload_app,node_predict_results toneMint
class node_train_data,node_weights,node_class_metadata toneRose
class node_camera toneIndigo
```

## Components

### Model training

- [Train and validate](https://github.com/arpit-kumar05/major_project/blob/main/train.py): `train.py`
- [Training CNN](https://github.com/arpit-kumar05/major_project/blob/main/train.py): `train.py`

### Prediction

- [Image preprocessing](https://github.com/arpit-kumar05/major_project/blob/main/app.py): `app.py`
- [Inference CNN](https://github.com/arpit-kumar05/major_project/blob/main/app.py): `app.py`
- [Class and confidence](https://github.com/arpit-kumar05/major_project/blob/main/app.py): `app.py`
- [Image preprocessing](https://github.com/arpit-kumar05/major_project/blob/main/predict.py): `predict.py`
- [Prediction CNN](https://github.com/arpit-kumar05/major_project/blob/main/predict.py): `predict.py`

### User interfaces

- [Detection dashboard](https://github.com/arpit-kumar05/major_project/blob/main/app.py): `app.py`
- [Live webcam processor](https://github.com/arpit-kumar05/major_project/blob/main/app.py): `app.py`
- [Dataset statistics view](https://github.com/arpit-kumar05/major_project/blob/main/app.py): `app.py`
- [Upload predictor](https://github.com/arpit-kumar05/major_project/blob/main/predict.py): `predict.py`
- [Prediction display](https://github.com/arpit-kumar05/major_project/blob/main/predict.py): `predict.py`

### Dataset and state

- [PlantVillage images](https://github.com/arpit-kumar05/major_project/tree/main/dataset/PlantVillage): `dataset/PlantVillage`
- [Saved model weights](https://github.com/arpit-kumar05/major_project/blob/main/models/plant_disease_model.pth): `models/plant_disease_model.pth`
- [Class metadata helpers](https://github.com/arpit-kumar05/major_project/blob/main/utils.py): `utils.py`

### Other components

- **User**
- **Camera**

## Connections

- Train and validate → PlantVillage images: loads and splits (evidence: `train.py`)
- Train and validate → Training CNN: trains and validates (evidence: `train.py`)
- Train and validate → Saved model weights: saves weights (evidence: `train.py`)
- User → Detection dashboard: submits image (evidence: `app.py`)
- Detection dashboard → Saved model weights: loads weights (evidence: `app.py`)
- Detection dashboard → Image preprocessing: prepares image (evidence: `app.py`)
- Image preprocessing → Inference CNN: provides tensor (evidence: `app.py`)
- Detection dashboard → Inference CNN: runs prediction (evidence: `app.py`)
- Inference CNN → Class and confidence: returns probabilities (evidence: `app.py`)
- Class and confidence → Detection dashboard: displays result (evidence: `app.py`)
- Camera → Live webcam processor: sends frames (evidence: `app.py`)
- Live webcam processor → Class and confidence: predicts each frame (evidence: `app.py`)
- Detection dashboard → Dataset statistics view: shows class counts (evidence: `app.py`)
- User → Upload predictor: uploads image (evidence: `predict.py`)
- Upload predictor → Saved model weights: loads weights (evidence: `predict.py`)
- Upload predictor → Image preprocessing: prepares image (evidence: `predict.py`)
- Upload predictor → Prediction CNN: runs prediction (evidence: `predict.py`)
- Prediction CNN → Prediction display: returns probabilities (evidence: `predict.py`)
- Prediction display → Upload predictor: displays result (evidence: `predict.py`)
