GeoGuessr Modelling

We trained a deep neural network that predicts the country of origin for a given image. The project tackles the challenging problem of geographical image classification with systematic data engineering and performance optimization.

The Challenge

Overview

The system uses transfer learning with a ResNet152 backbone combined with a custom classification head. Key achievements include:

Data Engineering

Architecture

Performance Optimization

The result is an accurate country predictor that efficiently processes large-scale geographical image data.

View on GitHub →