Inspiration

We wanted to combine our interest in neural networks, backend development with sence of humor. As well as kickstart our personal project.

What it does

Categorizes images based on their text content. Allowing easy searching in image based content.

How we built it

We built it using Google Cloud Vision and Tensorflow libraries, hacked together via Flask and Vue.js.

Challenges we ran into

We had to create our own dataset of meme classifications with time constraints. Learning javascript frameworks in a backend oriented team.

Accomplishments that we're proud of

We built our first ever deep neural network. We managed to reach our goald of building a working MVP at our first hackaton.

What we learned

We learned how to distribute tasks in a team effectively. We shouldn't eat so much, just because the food is free.

What's next for joke-categorizer

Gathering user feedback on generated categories. Incorporating into our new personal project. Generalization to be useful outside of meme classification.

Built With

Share this project:

Updates