This project is a part of the Graduate Rotational Internship Program (GRIP) offered by The Sparks Foundation. The goal of this project is to create a face mask detector using deep learning and computer vision techniques.
The face mask detector is built using a convolutional neural network (CNN) to classify images of people as wearing masks or not wearing masks. The dataset used for training and evaluating the model is obtained from Kaggle.
The "Face Mask Detection" dataset can be found on Kaggle at the following link: Face Mask Detection Dataset. The dataset contains 12,000 images, which are divided into three sets: training, validation, and testing.
- TensorFlow
- NumPy
- pandas
- OpenCV
- scikit-learn
- Matplotlib
- Set up a Kaggle notebook and import the required datase.
- Install the necessary libraries and import them in your notebook.
- Load and preprocess the dataset, splitting it into training, validation, and test sets.
- Define and compile the CNN model.
- Train the model using the training dataset and validate it using the validation dataset.
- Evaluate the model using the test dataset.
- Save the model for future use.
This project is released under the MIT License.