StarSmiles is a deep learning-powered API designed to classify dental X-rays, automating the detection of conditions like cavities, implants, and impacted teeth. Developed during the Le Wagon bootcamp, this project highlights my skills as a Machine Learning Engineer with strong backend development and project management experience.

• Automated Dental Diagnosis: Classifies X-rays into dental conditions (Cavity, Fillings, Implants, etc.).
• FastAPI Integration: Exposes the model via a production-ready API for seamless integration with dental clinics.
• Efficient Preprocessing & Training: Custom pipeline to handle and preprocess dental X-ray images.
• Scalable Architecture: Designed for future improvements, retraining, and deployment with Docker.

1. Clone the repository:

   git clone https://github.com/yourusername/project-starsmiles.git
   cd project-starsmiles
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Run the API:

   uvicorn starsmiles.api.fast:app --reload
   

4. Use the API: Send a POST request with an X-ray image to /predict.

**Ensure you have Docker installed on your machine. You can download and install Docker from **here.

**Ensure your **.env file contains the correct paths and environment variables. Here is an example:

TRAIN_DATA_DIR=raw_data/Dental_Radiography/train
TEST_DATA_DIR=raw_data/Dental_Radiography/test
VALID_DATA_DIR=raw_data/Dental_Radiography/valid
MODEL_PATH=/app/models/model.keras

Navigate to the root directory of your project and run the following command to build the Docker image:

make docker_build

Run the Docker container using the following command:

make docker_run

Check the logs to ensure the application is running correctly:

docker logs my-fastapi-container

**Open a web browser and navigate to **http://localhost:8000 to access your FastAPI application. You can also check the automatically generated API documentation at http://localhost:8000/docs.

Here are the example commands you should run from the root of your project directory:

1. Build Docker Image:

   make docker_build
   

2. Run Docker Container:

   make docker_run
   

3. Check Logs:

   docker logs my-fastapi-container
   

4. Access Application: Open a web browser and navigate to http://localhost:8000.

By following these steps, you should be able to build and run your Docker container locally.