Leaf Disease Detection on Images with Neural Networks Project.
Authors:
If you only want to use the web application to detect the disease or healthiness of a leaf.
Create a Virtual environment
python -m venv .venv
Activate the virtual environment (Windows):
.venv\Scripts\activate
Activate the virtual environment (macOS/Linux):
source .venv/bin/activate
Install the required Python packages:
pip install -r requirements.txt
Run the Application
cd src
python app.py
OR Build and run the docker image
docker compose up --build
The application will be available at http://localhost:5000.
Complete the simple setup first, then:
Build and run the docker image
docker compose up --build
This will start the MLflow server at http://localhost:5001.
Run the training script
cd src
python train_model_1.py
OR
cd src
python train_model_2.py
Install Anaconda here : anaconda.com/download
Install CUDA 11.2 here : developer.nvidia.com/cuda-11.2.2-download-archive
Download CUDNN 8.1.0 here : developer.nvidia.com/rdp/cudnn-archive
Create a new Python 3.8 enrionment
conda create -n leaveslife python=3.8
conda activate leaveslife
Install CUDA and CUDNN in the environment
conda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0
Install TensorFlow after CUDA and CUDNN
python -m pip install "tensorflow==2.10"
Install other dependencies
pip install -r requirements.txt
Build and run the docker image
docker compose up --build
This will start the MLflow server at http://localhost:5001.
Run the training script
cd src
python train_model_3.py