Model that detects health of a guava based on user uploaded image
Citation of dataset below

Requires Python (recommended to use virtual environment e.g., venv / virtualenv)

1. Clone Repository

git clone https://github.com/mnothman/guavadetector.git

2. Setup Environment (optional)

python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate

pip install -r requirements.txt

3. Download Dataset

Download dataset from: https://www.kaggle.com/datasets/asadullahgalib/guava-disease-dataset

Extract to: /data/
Full default path should be: /data/archive/GuavaDiseaseDataset
Can modify base directory of data in train.py: "BASE_DIR = /data/archive/GuavaDiseaseDataset"

4. Train Model

cd model
python train.py

wait for guava_disease_detector.keras to finish training

model/
└── guava_disease_detector.keras

5. Run the Flask App

start flask app:
cd app
python app.py

Open browser at http://localhost:5000/

guava-disease-detector/
│
├── app/
│ ├── app.py # Main Flask application
│ ├── static/
│ └── templates/
│ └── upload.html
│
│
├── data/archive/GuavaDiseaseDataset/
│ ├── test/
│ ├── train/
│ └── val/
│
├── model/
│ ├── guava_disease_detector.keras # Trained Model
│ ├── preprocess.py
│ └── train.py

Citation

Actual dataset from Mendeley Data:
Amin, Md Al; Mahmud, Md Iqbal; Rahman, Asadullah Bin; Parvin, Mst Aktarina; Mamun, Md Abdulla Al (2024), “Guava Fruit Disease Dataset”, Mendeley Data, V1, doi: 10.17632/bkdkc4n835.1

https://www.kaggle.com/datasets/asadullahgalib/guava-disease-dataset