AI-Mask-Detector using deep learning Convolutional neural network

Project COMP6721 - Applied Artificial Intelligence @ Concordia University

AI Mast Detector can analyze face images and detect whether a person is wearing a face mask or not, the type of mask that is being worn, and whether the mask is worn correctly. This model is trained on dataset of 2000 portraits, 1500 for training and 500 for testing. This model has accuracy of 95% with 97% F1-score.

hyper Parameters

• Image Dimensions = 256 * 256
• kernel_size= 3
• stride=2
• padding=2
• epochs= 45
• Optimiser: ADAM Optimiser. • Loss Function: Cross Entropy Loss • Learning Rate: 0.001

Instructions

-Download .ipynb file and run it either on google Collab or in Jupyter Notebook. -Adjust hyper parameter and dataset size as per your need.