Inspiration
The project prompt.
What it does
It attempts to unscramble images (with a low success rate).
How we built it
The ML model was built with keras (also tensorflow, numpy, and pandas). It was then deployed to streamlit via github.
Challenges we ran into
I had to learn all of ML from scratch which was hard. Since I had no experience, basic tasks like processing data and building the model took considerable amounts of time. Finally, I still need to adjust the layers because the accuracy is quite low.
Accomplishments that we're proud of
I'm proud of getting something that compiled and isn't entirely broken.
What we learned
A lot.
What's next for Unscrambling images
Getting it to work better.
Log in or sign up for Devpost to join the conversation.