The purpose of this repository is to create model to classifier plants and fruits using Tensorflow
My idea is to use computer vision models to identify fruits and provide nutritional information.
To get started, make sure to install all the necessary dependencies and packages listed in the provided YAML file.
conda env create -f env.yaml
You can also use pip to create the environment
python -m venv venv
source venv/bin/activate (Linux) / venv\Scripts\Activate.ps1 (Windows)
pip install -r requirements.txt
The dataset is publicly available in Kaggle and it has been extended using a fruit dataset
Due to computational limitations, the train model will be trained with 3 classes: bananas,coconuts, and aloevera. Here's a table of the models I've experimented with, along with their respective accuracy:
| Model | Accuracy | Classes |
|---|---|---|
| MobileNet V2 | 80% | bananas,coconuts, and aloevera |
The demo can be used
python -m streamlit run app.py
Bryan Piguave Email: [email protected] LinkedIn: Bryan Piguave