This project demonstrates an Image Classification deep learning neural network model built using TensorFlow. It classifies images of flowers by leveraging a dataset of labeled images. The project covers the entire pipeline: data preprocessing, model building, training, evaluation, and deployment as a web application.
- Data Preprocessing: Reads image datasets from folders and converts them into arrays for TensorFlow.
- Model Architecture: Builds a deep learning neural network using TensorFlow's Sequential API with multiple layers.
- Training & Evaluation: Trains the model on the dataset and evaluates its accuracy.
- Web Deployment: Deploys the trained model as a Flask-based web application for real-time predictions.
The dataset contains images of various flower species, organized into labeled folders. Each folder corresponds to a specific category (e.g., rose, tulip, daisy). You can download the dataset from here.
- Frontend: HTML, CSS, JavaScript for the web interface.
- Backend: Python (Flask Framework) for deploying the model.
- Deep Learning: TensorFlow for building and training the neural network model.
- Data Processing: NumPy and Pandas for handling image data.
- Python 3.6+: Install Python from here.
- Pip: For installing dependencies.
- TensorFlow: Deep learning library for model creation.
- Flask: Web framework for deploying the application.
- NumPy & Pandas: For data manipulation and processing.
- Install Python 3.6+ on your system from here.
- Clone the repository:
git clone https://github.com/hamzaelmassaoudy/Flower-Image-Classification-TensorFlow.git