Inspiration
While preparing for interviews, I thought this was a cool leetcode problem: https://leetcode.com/problems/design-twitter/description/.
And so for fun, wanted to kinda implement my own small social media with some Machine learning pizzaz!
What it does
You can upload images to our app. Our FastAPI application will run the MobileNetV2 image classifier on your image and find any relevant objects. Then this data, along with your images, are stored securely on our firebase backend.
How we built it
We used FastAPI for the backend and Keras for the machine learning model. We used ReactJS for the front end.
Challenges we ran into
Properly connecting our backend with our Firebase cloud storage was new to us.
Accomplishments that we're proud of
Our system (the frontend, backend, and cloud storage) all work seamlessly to provide one product. Its pretty cool.
What we learned
First time working with firebase and cloud storage. We plant to use this new knowledge for a lot of cool projects in the future!
What's next for Cloud Image Sharing with AI Classification!
We look forward to makign our frontend much nicer and cleaner. We also plan to add user support.
We plan on deploying the backend on fly.io and our front end on Netlify.
Built With
- fastapi
- javascript
- keras
- python
- react
- tensorflow
Log in or sign up for Devpost to join the conversation.