The Cat & Dog Classifier is a web-based image classification tool that leverages Convolutional Neural Networks (CNNs) to predict whether an uploaded image contains a cat or a dog. This project utilizes Flask, HTML, CSS, and JavaScript to provide a simple, user-friendly interface for image classification.

The task involves visualizing and analyzing scraped data from two review platforms to gain insights into tourism trends. The dataset, located in the full_stack_data.csv file, will serve as the foundation for building various components such as charts and tables.

This project develops a Deep Learning Model for facial emotion recognition, classifying seven emotions (Happy, Sad, Angry, Neutral, Surprise, Fear, Disgust) using the FER-2013 dataset. The model, achieving 70.13% accuracy, leverages advanced preprocessing (resizing, augmentation, class balancing) to handle dataset challenges like imbalance and mislabeling. Grad-CAM visualizations enhance explainability by highlighting key facial features (e.g., eyes, mouth) driving predictions.