This repo contains the code and documentation for my final year project on tea leaf diseases using deep learning as a partial fulfillment of my degree of master in science in information technology from the department of computer science, Gauhati university, Ghy-14
The complete folders including saved_models are in master branch instead of main branch
I used a publicly available dataset for tea leaf disease detection. The dataset is available in the data directory.
We trained four different machine learning models to classify tea leaf diseases. The models are saved in the saved_models directory. For more details about the models and their performance, refer to the project proposal/project report in the documentation directory.
VGG16withCustomLayers.ipynb: Jupyter Notebook for tea leaf disease detection using transfer learing technique: base model as VGG16.NasNetWithCustomLayers.ipynb: Jupyter Notebook for tea leaf disease detection using transfer learing technique: base model as NasNetMobile.InceptionV3.ipynb: Jupyter Notebook for tea leaf disease detection using transfer learing technique: base model as InceptionV3.Mysequential.ipynb: Jupyter Notebook for tea leaf disease detection using sequentail personal customized CNN model.
The trained models are saved in the saved_models directory.
We have developed a web application to allow users to interact with the trained models and get predictions for tea leaf diseases.
-
Home Page: The home page allow user to upload a dataset path or link and allow user to choose two trained models among the four machine learning models.
-
Comapre Page: The compare page shows the comparesion graph of the two selected models by the user in the home page along with the hyparperameters.
-
Predict Page: Users can select any model among the four train/saved model and give input images of tea leaf to detect the tea leaf disease
-
Result Page: Users get predictions for the type of disease affecting the tea leaves.
The documentation directory contains my project proposal, Report and assests. For more detailed information about the project, you can refer to the following documents:
Make sure you have the required version of Python (e.g., Python 3.7 or later) installed before proceeding.
-
To use this project, you need to have Python installed on your system.
-
Install the required dependencies using the following command:
pip install -r requirements.txt -
Open your terminal, navigate to where you want to save the project and and Clone this repository using
git clone https://github.com/jenishborah/Tea-Leaf-Disease-Detection -
Open and run the Jupyter Notebooks in the
notebooksdirectory in the specified order.
-
Navigate to the
web_appdirectory. -
Run the Flask application:
main.py -
Open your web browser and go to
http://localhost:5000to access the web application.
This project is licensed under the MIT License - see the LICENSE file for details.
Copyright (c) 2023 Jenish A borah