Cube Rule

Inspiration

Our project was inspired by the CSCI0220 staff theme of controversial sandwich. We took on the burden of answering this all-important question.

Through our app, we are able to classify any food item as a salad, toast, sandwich, taco, sushi, bread bowl, or calzone using deep learning.

We created a CNN using keras to classify an input image as one of the 7 classes listed above. We trained our model using Spell's GPUs.

The frontend of the app is built with react-native and the backend is built with flask.

Communication between frontend and backend sending images, very messy unlabeled image data sets.

Successfully deployed working CNN model on Spell's GPU. Successfully connected between react-native frontend and flask backend

We learned how to integrate frontend and backend and how to deploy on Spell's GPU.

SandwichCoin ICO

I helped create our image processing pipeline using Pillow and the Food101 dataset. I developed our CNN using Keras and successfully classified images using our network.

Dylan Sam
A student at Brown University studying Applied Mathematics and Computer Science looking to learn from attending hackathons.
I made the front of the the app using react-native and interfaced with the back-end to send images and process the response.

glee43
Daniel Ritter
Tyler Jiang
Julia McClellan

Leave feedback in the comments!

Log in or sign up for Devpost to join the conversation.