MediLeaf-AI

MediLeaf is an application whose motive is to help the individual identify medicinal plants with their properties by just scanning the leaf of any plant which might create curiosity about the plant that leads to the preservation of the valuable plants. This is also an end-to-end deep learning project focusing from development to deployment. You can train your model and deploy it into the FastAPI here.

Currently, mediLeaf can fairly classify 30 different species of plants by using their leaf images.

Scientific Name
Alpinia Galanga
Amaranthus Viridis
Artocarpus Heterophyllus
Azadirachta Indica
Basella Alba
Brassica Juncea
Carissa Carandas
Citrus Limon
Ficus Auriculata
Ficus Religiosa
Hibiscus Rosa-sinensis
Jasminum
Mangifera Indica
Mentha
Moringa Oleifera
Muntingia Calabura
Murraya Koenigii
Nerium Oleander
Nyctanthes Arbor-tristis
Ocimum Tenuiflorum
Piper Betle
Plectranthus Amboinicus
Pongamia Pinnata
Psidium Guajava
Punica Granatum
Santalum Album
Syzygium Cumini
Syzygium Jambos
Tabernaemontana Divaricata
Trigonella Foenum-graecum

Workflows

1. Update config.yaml
2. Update secrets.yaml [Optional]
3. Update params.yaml
4. Update the entity
5. Update the configuration manager in src config
6. Update the components
7. Update the pipeline
8. Update the main.py
9. Update the dvc.yaml

How to Train?

A. Normal way of training

1. Clone the repository

git clone https://github.com/surajkarki66/MediLeaf_AI

2. Create a Python virtual environment and activate the environment based on your machine(Linux, MacOS, and Windows)

3. Install the requirements

pip install -r requirements.txt

3. Run the following command

# Finally run the following command
python main.py

Now,

Model training will start soon

Note: Check params.yaml to tweak the configuration of the model.

B. Using MLops tool DVC for training

1. First run

dvc repro

2. Then,

dvc dag

Running Prediction API using Docker

1. Run the following docker command

    docker compose up --build

You can perform classification using the API endpoint: http://0.0.0.0:8000/api/v1/classify/

Running Prediction API Locally

1. Create a Python virtual environment and activate the environment based on your machine(Linux, MacOS, and Windows)

2. Install the dependencies

    pip install -r requirements.txt

3. Run the api server

   python service.py

You can perform classification using the API endpoint: http://0.0.0.0:8000/api/v1/classify/