Generative AI Pictionary

Role
Full-Stack Developer
Timeline
Sep–Dec 2024, 4 months
Tools
Python, Pygame, TensorFlow, Keras

Problem

Build an application that meaningfully leverages generative AI.

Constraints

Had to use an existing dataset of drawings to train the GAN and CNN models.

Hypothesis

The Google Quick Draw dataset, with 50 million images across 345 categories, would provide sufficient diversity to train both recognition and generation models effectively.

Process

Solution

A game with a custom-trained AI opponent that can both recognize player drawings and generate its own.

Metrics

Evidence

Lessons Learned

Learned how to train GAN and CNN models on image datasets for image classification and generation.