Flower Classifier Project

This project demonstrates image classification of flowers using TensorFlow and Keras, with data augmentation and model export to TensorFlow Lite. The workflow is implemented in the Jupyter notebook dataAug26.ipynb.

Getting Started

1. Create a Python Environment

It is recommended to use Python 3.12.12 for this project. You can use venv or conda to create a virtual environment.

Using venv:

python3.12 -m venv venv
source venv/bin/activate

Using conda:

conda create -n flower-env python=3.12.12
conda activate flower-env

2. Install Dependencies

Install the required Python packages:

pip install matplotlib numpy opencv-python pillow tensorflow scikit-learn

• matplotlib
• numpy
• opencv-python
• pillow
• tensorflow
• scikit-learn

3. Run the Notebook

Open the notebook in VS Code or Jupyter:

jupyter notebook dataAug26.ipynb

Or, in VS Code, open the file and run the cells interactively.

---

Notes

• Be sure to install the Jupyter extension if you're using VSCode.
• You will require ipykernel to get jupyter working, but if you're using VSCode, it should prompt you to install it as you try and run the first cell.
• The notebook downloads a flower dataset and demonstrates model training, evaluation, and export to TFLite.
• For TFLite model usage in React Native, see the instructions at the end of the notebook.

---

Happy Coding!